Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0916. Min Act: -0.1474
Data Index: 5022131 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.1083. Min Act: -0.1372
Data Index: 2444640 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0580. Min Act: -0.1575
Data Index: 8723260 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0580. Min Act: -0.1643
Data Index: 8071688 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0748. Min Act: -0.1372
Data Index: 8588679 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0748. Min Act: -0.1372
Data Index: 3802625 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0748. Min Act: -0.1372
Data Index: 8237105 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0580. Min Act: -0.1372
Data Index: 4095363 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1372
Data Index: 3866251 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0244. Min Act: -0.1372
Data Index: 2051131 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0580. Min Act: -0.1699
Data Index: 1895173 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1372
Data Index: 2384454 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1372
Data Index: 7555123 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1372
Data Index: 899058 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0244. Min Act: -0.1372
Data Index: 3599188 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1522
Data Index: 4173728 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0412. Min Act: -0.1699
Data Index: 7130550 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0244. Min Act: -0.1372
Data Index: 1070765 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0244. Min Act: -0.1372
Data Index: 5784781 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1083. Min Range: -2.1083
Max Act: 2.0244. Min Act: -0.1537
Data Index: 5164800 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19