transformer-lens-interpretability

from transformer_lens import HookedTransformer

# Load a model
model = HookedTransformer.from_pretrained("gpt2-small")

# For gated models (LLaMA, Mistral)
import os
os.environ["HF_TOKEN"] = "your_token"
model = HookedTransformer.from_pretrained("meta-llama/Llama-2-7b-hf")

# Get all activations
tokens = model.to_tokens("The Eiffel Tower is in")
logits, cache = model.run_with_cache(tokens)

# Access specific activations
residual = cache["resid_post", 5]  # Layer 5 residual stream
attn_pattern = cache["pattern", 3]  # Layer 3 attention pattern
mlp_out = cache["mlp_out", 7]  # Layer 7 MLP output

# Filter which activations to cache (saves memory)
logits, cache = model.run_with_cache(
    tokens,
    names_filter=lambda name: "resid_post" in name
)

from transformer_lens import HookedTransformer, patching
import torch

model = HookedTransformer.from_pretrained("gpt2-small")

# 1. Define clean and corrupted prompts
clean_prompt = "The Eiffel Tower is in the city of"
corrupted_prompt = "The Colosseum is in the city of"

clean_tokens = model.to_tokens(clean_prompt)
corrupted_tokens = model.to_tokens(corrupted_prompt)

# 2. Get clean activations
_, clean_cache = model.run_with_cache(clean_tokens)

# 3. Define metric (e.g., logit difference)
paris_token = model.to_single_token(" Paris")
rome_token = model.to_single_token(" Rome")

def metric(logits):
    return logits[0, -1, paris_token] - logits[0, -1, rome_token]

# 4. Patch each position and layer
results = torch.zeros(model.cfg.n_layers, clean_tokens.shape[1])

for layer in range(model.cfg.n_layers):
    for pos in range(clean_tokens.shape[1]):
        def patch_hook(activation, hook):
            activation[0, pos] = clean_cache[hook.name][0, pos]
            return activation

        patched_logits = model.run_with_hooks(
            corrupted_tokens,
            fwd_hooks=[(f"blocks.{layer}.hook_resid_post", patch_hook)]
        )
        results[layer, pos] = metric(patched_logits)

# 5. Visualize results (layer x position heatmap)

from transformer_lens import HookedTransformer
import torch

model = HookedTransformer.from_pretrained("gpt2-small")

# IOI task: "When John and Mary went to the store, Mary gave a bottle to"
# Model should predict "John" (indirect object)

prompt = "When John and Mary went to the store, Mary gave a bottle to"
tokens = model.to_tokens(prompt)

# 1. Get baseline logits
logits, cache = model.run_with_cache(tokens)

john_token = model.to_single_token(" John")
mary_token = model.to_single_token(" Mary")

# 2. Compute logit difference (IO - S)
logit_diff = logits[0, -1, john_token] - logits[0, -1, mary_token]
print(f"Logit difference: {logit_diff.item():.3f}")

# 3. Direct logit attribution by head
def get_head_contribution(layer, head):
    # Project head output to logits
    head_out = cache["z", layer][0, :, head, :]  # [pos, d_head]
    W_O = model.W_O[layer, head]  # [d_head, d_model]
    W_U = model.W_U  # [d_model, vocab]

    # Head contribution to logits at final position
    contribution = head_out[-1] @ W_O @ W_U
    return contribution[john_token] - contribution[mary_token]

# 4. Map all heads
head_contributions = torch.zeros(model.cfg.n_layers, model.cfg.n_heads)
for layer in range(model.cfg.n_layers):
    for head in range(model.cfg.n_heads):
        head_contributions[layer, head] = get_head_contribution(layer, head)

# 5. Identify top contributing heads (name movers, backup name movers)

# WRONG: Old hooks remain active
model.run_with_hooks(tokens, fwd_hooks=[...])  # Debug, add new hooks
model.run_with_hooks(tokens, fwd_hooks=[...])  # Old hooks still there!

# RIGHT: Always reset hooks
model.reset_hooks()
model.run_with_hooks(tokens, fwd_hooks=[...])

# WRONG: Assuming consistent tokenization
model.to_tokens("Tim")  # Single token
model.to_tokens("Neel")  # Becomes "Ne" + "el" (two tokens!)

# RIGHT: Check tokenization explicitly
tokens = model.to_tokens("Neel", prepend_bos=False)
print(model.to_str_tokens(tokens))  # ['Ne', 'el']

# WRONG: Ignoring LayerNorm
pre_activation = residual @ model.W_in[layer]

# RIGHT: Include LayerNorm
ln_scale = model.blocks[layer].ln2.w
ln_out = model.blocks[layer].ln2(residual)
pre_activation = ln_out @ model.W_in[layer]

# Use selective caching
logits, cache = model.run_with_cache(
    tokens,
    names_filter=lambda n: "resid_post" in n or "pattern" in n,
    device="cpu"  # Cache on CPU
)