Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2455. Min Range: -7.2455
Max Act: 7.2455. Min Act: -0.1700
Data Index: 3133364 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2455. Min Range: -7.2455
Max Act: 7.0268. Min Act: -0.1700
Data Index: 3125148 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2455. Min Range: -7.2455
Max Act: 7.0268. Min Act: -0.1700
Data Index: 6161828 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.9643. Min Act: -0.1700
Data Index: 6425336 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.8393. Min Act: -0.1700
Data Index: 1398225 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7455. Min Act: -0.1700
Data Index: 8645709 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7768. Min Act: -0.1700
Data Index: 3532009 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7455. Min Act: -0.1700
Data Index: 1053625 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7143. Min Act: -0.1700
Data Index: 3411593 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7143. Min Act: -0.1700
Data Index: 3816802 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7143. Min Act: -0.1700
Data Index: 4888532 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.7143. Min Act: -0.1700
Data Index: 426454 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6518. Min Act: -0.1700
Data Index: 4588182 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6518. Min Act: -0.1700
Data Index: 4002263 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6205. Min Act: -0.1700
Data Index: 8196502 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6205. Min Act: -0.1700
Data Index: 1137281 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6205. Min Act: -0.1700
Data Index: 2155383 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.5893. Min Act: -0.1700
Data Index: 3855104 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.6205. Min Act: -0.1700
Data Index: 4925033 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2455. Min Range: -7.2455
Max Act: 6.5893. Min Act: -0.1700
Data Index: 437660 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19