Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2344. Min Range: -8.2344
Max Act: 8.2344. Min Act: -0.1700
Data Index: 4308482 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.8281. Min Act: -0.1700
Data Index: 2885505 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.7031. Min Act: -0.1700
Data Index: 7431739 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.6406. Min Act: -0.1700
Data Index: 3547395 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.6094. Min Act: -0.1700
Data Index: 5280284 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.6094. Min Act: -0.1700
Data Index: 4434076 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.6094. Min Act: -0.1700
Data Index: 5767842 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.5781. Min Act: -0.1700
Data Index: 4308483 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.5156. Min Act: -0.1700
Data Index: 4434084 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.5156. Min Act: -0.1700
Data Index: 7216976 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.4844. Min Act: -0.1700
Data Index: 7231124 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.4531. Min Act: -0.1700
Data Index: 2667233 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.3281. Min Act: -0.1700
Data Index: 7545876 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.2969. Min Act: -0.1700
Data Index: 8099318 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.2969. Min Act: -0.1700
Data Index: 4519967 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.2031. Min Act: -0.1700
Data Index: 400566 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.1719. Min Act: -0.1700
Data Index: 7246966 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.1719. Min Act: -0.1700
Data Index: 1604685 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.1719. Min Act: -0.1700
Data Index: 938184 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2344. Min Range: -8.2344
Max Act: 7.2031. Min Act: -0.1700
Data Index: 41501 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19