Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 376 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.0419. Min Range: -14.0419
Max Act: 14.0419. Min Act: -0.1700
Data Index: 5108680 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0419. Min Range: -14.0419
Max Act: 13.1669. Min Act: -0.1700
Data Index: 1531688 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.9794. Min Act: -0.1700
Data Index: 5927080 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.7294. Min Act: -0.1700
Data Index: 3770342 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.6669. Min Act: -0.1700
Data Index: 1554271 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.6044. Min Act: -0.1700
Data Index: 5165769 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.5419. Min Act: -0.1700
Data Index: 4445188 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.4169. Min Act: -0.1700
Data Index: 2607688 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.4169. Min Act: -0.1700
Data Index: 6362015 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.2294. Min Act: -0.1700
Data Index: 5972994 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.2294. Min Act: -0.1700
Data Index: 2710690 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.2294. Min Act: -0.1698
Data Index: 4133313 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.1044. Min Act: -0.1700
Data Index: 6973959 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.1044. Min Act: -0.1700
Data Index: 3334104 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.1044. Min Act: -0.1700
Data Index: 7211565 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.1044. Min Act: -0.1700
Data Index: 551816 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.0419. Min Act: -0.1700
Data Index: 5222781 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0419. Min Range: -14.0419
Max Act: 12.0419. Min Act: -0.1700
Data Index: 4708553 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0419. Min Range: -14.0419
Max Act: 11.9794. Min Act: -0.1700
Data Index: 6126711 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0419. Min Range: -14.0419
Max Act: 11.9794. Min Act: -0.1700
Data Index: 5791114 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19