Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0813. Min Range: -12.0813
Max Act: 12.0813. Min Act: -0.1700
Data Index: 778514 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.8938. Min Act: -0.1700
Data Index: 5528081 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.5813. Min Act: -0.1700
Data Index: 623637 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.5188. Min Act: -0.1700
Data Index: 4736335 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.5188. Min Act: -0.1700
Data Index: 3995316 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.4563. Min Act: -0.1700
Data Index: 5758838 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.4563. Min Act: -0.1700
Data Index: 6532275 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.5188. Min Act: -0.1699
Data Index: 7341574 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.3938. Min Act: -0.1700
Data Index: 7358032 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.3938. Min Act: -0.1700
Data Index: 5655658 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.4563. Min Act: -0.1700
Data Index: 6621470 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.3313. Min Act: -0.1700
Data Index: 8486715 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.3313. Min Act: -0.1700
Data Index: 6229080 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.2063. Min Act: -0.1700
Data Index: 3833707 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.2688. Min Act: -0.1700
Data Index: 6578239 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.2688. Min Act: -0.1700
Data Index: 758847 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.2063. Min Act: -0.1700
Data Index: 3188366 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.1438. Min Act: -0.1700
Data Index: 2624000 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.0813. Min Act: -0.1700
Data Index: 6204887 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0813. Min Range: -12.0813
Max Act: 11.0188. Min Act: -0.1700
Data Index: 4064837 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19