Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.6413. Min Act: -0.1700
Data Index: 4646238 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.4226. Min Act: -0.1700
Data Index: 7832624 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.3913. Min Act: -0.1700
Data Index: 285871 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.4226. Min Act: -0.1700
Data Index: 7323208 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.3913. Min Act: -0.1700
Data Index: 1171940 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.3601. Min Act: -0.1700
Data Index: 2131031 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.3288. Min Act: -0.1700
Data Index: 7228000 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.3288. Min Act: -0.1700
Data Index: 5921620 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2976. Min Act: -0.1700
Data Index: 7824399 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2976. Min Act: -0.1700
Data Index: 6808413 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2663. Min Act: -0.1700
Data Index: 5552840 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2351. Min Act: -0.1700
Data Index: 1251659 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2351. Min Act: -0.1700
Data Index: 5022335 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2038. Min Act: -0.1700
Data Index: 7570384 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.2038. Min Act: -0.1700
Data Index: 652585 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.1726. Min Act: -0.1700
Data Index: 6265494 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.1726. Min Act: -0.1700
Data Index: 5627229 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.1726. Min Act: -0.1700
Data Index: 7832625 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.1726. Min Act: -0.1700
Data Index: 1053347 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6413. Min Range: -6.6413
Max Act: 6.1726. Min Act: -0.1700
Data Index: 6634178 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19