Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5679. Min Range: -6.5679
Max Act: 6.5679. Min Act: -0.1700
Data Index: 4855717 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5679. Min Range: -6.5679
Max Act: 6.1929. Min Act: -0.1700
Data Index: 2982710 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5679. Min Range: -6.5679
Max Act: 6.1617. Min Act: -0.1700
Data Index: 125890 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5679. Min Range: -6.5679
Max Act: 6.0367. Min Act: -0.1700
Data Index: 4678823 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.9429. Min Act: -0.1700
Data Index: 6217665 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.9117. Min Act: -0.1700
Data Index: 553455 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.8804. Min Act: -0.1700
Data Index: 635280 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.8179. Min Act: -0.1700
Data Index: 1615955 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3572817 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6806488 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7867. Min Act: -0.1700
Data Index: 1963122 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7867. Min Act: -0.1700
Data Index: 2324211 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 369523 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 2495443 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 187033 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 2592748 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 1987328 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7554. Min Act: -0.1700
Data Index: 4990995 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.7242. Min Act: -0.1700
Data Index: 1126150 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5679. Min Range: -6.5679
Max Act: 5.6929. Min Act: -0.1700
Data Index: 784098 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19