Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 1904928 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 7594369 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4438202 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.5460. Min Act: -0.1700
Data Index: 306964 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5443533 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 4145524 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 7029500 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5339527 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 7797131 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4835. Min Act: -0.1700
Data Index: 7179743 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 2677770 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 4223179 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 4235913 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 8555602 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.3585. Min Act: -0.1700
Data Index: 5106610 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.4210. Min Act: -0.1700
Data Index: 6943663 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 3717674 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 6238550 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.3585. Min Act: -0.1700
Data Index: 6264179 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6085. Min Range: -8.6085
Max Act: 8.2960. Min Act: -0.1700
Data Index: 6392733 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19