Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.7861. Min Act: -0.1700
Data Index: 3957718 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.7079. Min Act: -0.1700
Data Index: 3103325 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6609. Min Act: -0.1700
Data Index: 1815926 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6453. Min Act: -0.1700
Data Index: 4653674 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6453. Min Act: -0.1700
Data Index: 5880344 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.6296. Min Act: -0.1700
Data Index: 8635497 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5670. Min Act: -0.1700
Data Index: 6141151 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5357. Min Act: -0.1700
Data Index: 938085 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5357. Min Act: -0.1700
Data Index: 7164742 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5514. Min Act: -0.1700
Data Index: 4824870 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.5201. Min Act: -0.1700
Data Index: 5711190 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4731. Min Act: -0.1700
Data Index: 2960310 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 4284527 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 4183590 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 3432282 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4887. Min Act: -0.1700
Data Index: 6969298 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4731. Min Act: -0.1700
Data Index: 8011789 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4417. Min Act: -0.1700
Data Index: 8313613 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4574. Min Act: -0.1700
Data Index: 4437782 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7861. Min Range: -3.7861
Max Act: 3.4731. Min Act: -0.1700
Data Index: 2796532 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19