Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4233. Min Act: -0.1700
Data Index: 2316675 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4233. Min Act: -0.1700
Data Index: 3321351 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4390. Min Act: -0.1700
Data Index: 7430759 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3606. Min Act: -0.1700
Data Index: 2222889 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3606. Min Act: -0.1700
Data Index: 1886485 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 7242196 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3292. Min Act: -0.1700
Data Index: 359849 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3135. Min Act: -0.1700
Data Index: 1886483 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2978. Min Act: -0.1700
Data Index: 1382821 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2978. Min Act: -0.1700
Data Index: 8380329 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2978. Min Act: -0.1700
Data Index: 117234 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2978. Min Act: -0.1700
Data Index: 2176416 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2507. Min Act: -0.1700
Data Index: 2571072 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2664. Min Act: -0.1700
Data Index: 3163654 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2664. Min Act: -0.1700
Data Index: 4578925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2507. Min Act: -0.1700
Data Index: 5570721 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2193. Min Act: -0.1700
Data Index: 1802118 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2350. Min Act: -0.1700
Data Index: 613750 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2350. Min Act: -0.1700
Data Index: 7430760 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.2507. Min Act: -0.1700
Data Index: 6923847 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19