Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0898. Min Range: -8.0898
Max Act: 8.0898. Min Act: -0.1700
Data Index: 1690757 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.9960. Min Act: -0.1700
Data Index: 6470942 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.9648. Min Act: -0.1700
Data Index: 6932984 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.9648. Min Act: -0.1700
Data Index: 732745 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.9335. Min Act: -0.1700
Data Index: 7323383 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7773. Min Act: -0.1700
Data Index: 6711109 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.8085. Min Act: -0.1700
Data Index: 6559844 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7773. Min Act: -0.1700
Data Index: 7108566 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7148. Min Act: -0.1700
Data Index: 524336 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7460. Min Act: -0.1700
Data Index: 918417 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7773. Min Act: -0.1700
Data Index: 1685052 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7773. Min Act: -0.1700
Data Index: 6581458 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6835. Min Act: -0.1700
Data Index: 7576479 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6835. Min Act: -0.1700
Data Index: 1150593 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6835. Min Act: -0.1700
Data Index: 3223073 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.7460. Min Act: -0.1700
Data Index: 5535763 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6523. Min Act: -0.1700
Data Index: 1857337 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6210. Min Act: -0.1700
Data Index: 3384676 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6523. Min Act: -0.1700
Data Index: 7986457 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0898. Min Range: -8.0898
Max Act: 7.6210. Min Act: -0.1700
Data Index: 1669982 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19