Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.7917. Min Act: -0.1700
Data Index: 61666 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.7292. Min Act: -0.1700
Data Index: 6154594 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6980. Min Act: -0.1700
Data Index: 8485111 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6355. Min Act: -0.1700
Data Index: 319528 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6355. Min Act: -0.1700
Data Index: 6598866 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6355. Min Act: -0.1700
Data Index: 5655118 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6355. Min Act: -0.1700
Data Index: 4070218 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 8258761 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 5614994 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 6955886 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 4220949 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6355. Min Act: -0.1700
Data Index: 6184562 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 6001263 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.5730. Min Act: -0.1700
Data Index: 5072797 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.6042. Min Act: -0.1700
Data Index: 6231177 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.5730. Min Act: -0.1700
Data Index: 3697998 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.5730. Min Act: -0.1700
Data Index: 4070221 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.5417. Min Act: -0.1700
Data Index: 8591629 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.5105. Min Act: -0.1700
Data Index: 3174741 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7917. Min Range: -4.7917
Max Act: 4.4792. Min Act: -0.1700
Data Index: 3593844 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19