Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.8497. Min Act: -0.1700
Data Index: 1663865 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.8497. Min Act: -0.1700
Data Index: 5926732 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.7247. Min Act: -0.1700
Data Index: 4661297 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.6622. Min Act: -0.1700
Data Index: 6588844 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.5372. Min Act: -0.1700
Data Index: 2317705 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.4747. Min Act: -0.1700
Data Index: 2282081 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.4747. Min Act: -0.1700
Data Index: 6358247 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.4747. Min Act: -0.1700
Data Index: 7011961 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.4122. Min Act: -0.1700
Data Index: 5140486 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 6683794 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.4122. Min Act: -0.1700
Data Index: 4811605 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 1513338 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 1467704 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 2577637 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.2872. Min Act: -0.1700
Data Index: 6530557 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 4305846 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 1195989 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 4010145 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.3497. Min Act: -0.1700
Data Index: 3611779 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.8497. Min Range: -14.8497
Max Act: 14.2872. Min Act: -0.1700
Data Index: 40622 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19