Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1734. Min Range: -10.1734
Max Act: 10.1734. Min Act: -0.1700
Data Index: 6732075 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1734. Min Range: -10.1734
Max Act: 10.0484. Min Act: -0.1700
Data Index: 5549265 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1734. Min Range: -10.1734
Max Act: 10.0484. Min Act: -0.1700
Data Index: 1649739 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.9234. Min Act: -0.1700
Data Index: 2927894 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.8609. Min Act: -0.1700
Data Index: 7355142 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6109. Min Act: -0.1700
Data Index: 2434745 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6734. Min Act: -0.1700
Data Index: 6671666 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6734. Min Act: -0.1700
Data Index: 1588423 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6734. Min Act: -0.1700
Data Index: 6620192 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6734. Min Act: -0.1700
Data Index: 613584 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.6109. Min Act: -0.1700
Data Index: 7579340 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 1146571 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 2759453 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.5484. Min Act: -0.1700
Data Index: 4216258 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 1996275 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 624992 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.4859. Min Act: -0.1700
Data Index: 1982201 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.4234. Min Act: -0.1700
Data Index: 3306984 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.4234. Min Act: -0.1700
Data Index: 6612430 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1734. Min Range: -10.1734
Max Act: 9.3609. Min Act: -0.1700
Data Index: 1488697 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19