Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0227. Min Range: -8.0227
Max Act: 8.0227. Min Act: -0.1700
Data Index: 1059081 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.9602. Min Act: -0.1700
Data Index: 1717512 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.7727. Min Act: -0.1700
Data Index: 1610908 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.7102. Min Act: -0.1700
Data Index: 4959661 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.7102. Min Act: -0.1700
Data Index: 2858008 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.6477. Min Act: -0.1700
Data Index: 3591352 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.5540. Min Act: -0.1700
Data Index: 3279678 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.5540. Min Act: -0.1700
Data Index: 4959669 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.5540. Min Act: -0.1700
Data Index: 3499825 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.4602. Min Act: -0.1700
Data Index: 3279675 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.5227. Min Act: -0.1700
Data Index: 4786407 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.4290. Min Act: -0.1700
Data Index: 366955 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.4602. Min Act: -0.1700
Data Index: 3751973 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.3665. Min Act: -0.1700
Data Index: 40901 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.3665. Min Act: -0.1700
Data Index: 3552149 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.3352. Min Act: -0.1700
Data Index: 8184594 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.3040. Min Act: -0.1700
Data Index: 366958 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.3040. Min Act: -0.1700
Data Index: 4959676 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.2415. Min Act: -0.1700
Data Index: 4833186 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0227. Min Range: -8.0227
Max Act: 7.2727. Min Act: -0.1700
Data Index: 1644511 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19