Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0813. Min Range: -13.0813
Max Act: 13.0813. Min Act: -0.1700
Data Index: 725080 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.7063. Min Act: -0.1700
Data Index: 7028035 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.5813. Min Act: -0.1700
Data Index: 4856462 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.4563. Min Act: -0.1700
Data Index: 3589850 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.4563. Min Act: -0.1700
Data Index: 3411003 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.2688. Min Act: -0.1700
Data Index: 5660602 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.2688. Min Act: -0.1700
Data Index: 1542074 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.1438. Min Act: -0.1700
Data Index: 8048180 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.1438. Min Act: -0.1700
Data Index: 1053305 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.0813. Min Act: -0.1700
Data Index: 2240773 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0813. Min Range: -13.0813
Max Act: 12.0188. Min Act: -0.1700
Data Index: 1269969 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.8938. Min Act: -0.1700
Data Index: 4547354 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.9563. Min Act: -0.1700
Data Index: 531548 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.8938. Min Act: -0.1700
Data Index: 779477 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.8938. Min Act: -0.1700
Data Index: 5822881 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.8313. Min Act: -0.1700
Data Index: 7573483 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.7688. Min Act: -0.1700
Data Index: 8240599 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.7688. Min Act: -0.1700
Data Index: 4739867 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.7688. Min Act: -0.1700
Data Index: 4917751 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0813. Min Range: -13.0813
Max Act: 11.7688. Min Act: -0.1700
Data Index: 1804496 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19