Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.6989. Min Act: -0.1700
Data Index: 39201 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.6364. Min Act: -0.1700
Data Index: 2691374 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.6051. Min Act: -0.1700
Data Index: 6516572 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.4801. Min Act: -0.1700
Data Index: 1536061 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.4489. Min Act: -0.1700
Data Index: 4896006 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.4489. Min Act: -0.1700
Data Index: 4507901 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3864. Min Act: -0.1700
Data Index: 8803390 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.4176. Min Act: -0.1700
Data Index: 4287468 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.4176. Min Act: -0.1700
Data Index: 5045400 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3864. Min Act: -0.1700
Data Index: 6322819 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3864. Min Act: -0.1700
Data Index: 8671367 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3864. Min Act: -0.1700
Data Index: 3657187 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3239. Min Act: -0.1700
Data Index: 356278 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3239. Min Act: -0.1700
Data Index: 8691107 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3551. Min Act: -0.1700
Data Index: 2691373 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.3239. Min Act: -0.1700
Data Index: 376994 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.2926. Min Act: -0.1700
Data Index: 5389800 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.2614. Min Act: -0.1700
Data Index: 3679383 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.2926. Min Act: -0.1700
Data Index: 4605415 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6989. Min Range: -4.6989
Max Act: 4.2926. Min Act: -0.1700
Data Index: 6516573 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19