Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2975. Min Range: -12.2975
Max Act: 12.2975. Min Act: -0.1700
Data Index: 3621844 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2975. Min Range: -12.2975
Max Act: 12.2350. Min Act: -0.1700
Data Index: 7816171 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2975. Min Range: -12.2975
Max Act: 12.1725. Min Act: -0.1700
Data Index: 7611364 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2975. Min Range: -12.2975
Max Act: 12.2350. Min Act: -0.1700
Data Index: 2423938 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2975. Min Range: -12.2975
Max Act: 12.0475. Min Act: -0.1700
Data Index: 7116533 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.9850. Min Act: -0.1700
Data Index: 3000061 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.9850. Min Act: -0.1700
Data Index: 615713 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.9225. Min Act: -0.1700
Data Index: 4040883 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.9225. Min Act: -0.1700
Data Index: 234660 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.8600. Min Act: -0.1700
Data Index: 5228465 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6725. Min Act: -0.1700
Data Index: 5663526 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.7350. Min Act: -0.1700
Data Index: 4833412 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6100. Min Act: -0.1700
Data Index: 3992966 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6725. Min Act: -0.1700
Data Index: 5805284 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6725. Min Act: -0.1700
Data Index: 6667838 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6100. Min Act: -0.1700
Data Index: 4857979 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6100. Min Act: -0.1700
Data Index: 3922654 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6100. Min Act: -0.1700
Data Index: 1936931 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.6100. Min Act: -0.1700
Data Index: 6637636 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2975. Min Range: -12.2975
Max Act: 11.5475. Min Act: -0.1700
Data Index: 7623394 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19