Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5362. Min Range: -7.5362
Max Act: 7.5362. Min Act: -0.1700
Data Index: 1241651 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5362. Min Range: -7.5362
Max Act: 7.4112. Min Act: -0.1700
Data Index: 1726928 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5362. Min Range: -7.5362
Max Act: 7.1925. Min Act: -0.1700
Data Index: 3517373 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.9737. Min Act: -0.1700
Data Index: 3216630 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.8800. Min Act: -0.1700
Data Index: 3417168 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.8487. Min Act: -0.1700
Data Index: 3441939 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7862. Min Act: -0.1700
Data Index: 416589 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7550. Min Act: -0.1700
Data Index: 5219880 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7550. Min Act: -0.1700
Data Index: 5290075 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7550. Min Act: -0.1700
Data Index: 841517 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7550. Min Act: -0.1700
Data Index: 8371492 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6953923 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7237. Min Act: -0.1700
Data Index: 728134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.7237. Min Act: -0.1700
Data Index: 4212032 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.6925. Min Act: -0.1700
Data Index: 180645 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.6300. Min Act: -0.1700
Data Index: 7026159 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.6300. Min Act: -0.1700
Data Index: 2470165 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.6300. Min Act: -0.1700
Data Index: 817776 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.6300. Min Act: -0.1700
Data Index: 6557410 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5362. Min Range: -7.5362
Max Act: 6.5675. Min Act: -0.1700
Data Index: 8299096 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19