Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 408 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.9306. Min Act: -0.1700
Data Index: 5695783 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.8993. Min Act: -0.1700
Data Index: 6239882 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.8056. Min Act: -0.1700
Data Index: 3458034 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.7743. Min Act: -0.1700
Data Index: 659309 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2655581 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6806. Min Act: -0.1700
Data Index: 3406 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6493. Min Act: -0.1700
Data Index: 3756546 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6181. Min Act: -0.1700
Data Index: 7507168 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6181. Min Act: -0.1700
Data Index: 8517178 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6181. Min Act: -0.1700
Data Index: 6111400 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6181. Min Act: -0.1700
Data Index: 368064 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.6181. Min Act: -0.1700
Data Index: 5496475 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5868. Min Act: -0.1700
Data Index: 4408646 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 2534090 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5556. Min Act: -0.1700
Data Index: 315100 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 7114881 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 5095497 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 5427035 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 2060298 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9306. Min Range: -4.9306
Max Act: 4.5243. Min Act: -0.1700
Data Index: 5663247 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19