Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.5159. Min Act: -0.1700
Data Index: 7626239 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.5321. Min Act: -0.1700
Data Index: 1549575 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.5159. Min Act: -0.1700
Data Index: 7794406 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4997. Min Act: -0.1700
Data Index: 784811 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4997. Min Act: -0.1700
Data Index: 6237175 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4835. Min Act: -0.1700
Data Index: 4758715 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4511. Min Act: -0.1700
Data Index: 6807662 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4835. Min Act: -0.1700
Data Index: 5346009 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4835. Min Act: -0.1700
Data Index: 7536613 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4673. Min Act: -0.1699
Data Index: 5731462 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4835. Min Act: -0.1700
Data Index: 1060861 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4673. Min Act: -0.1700
Data Index: 4553671 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4673. Min Act: -0.1700
Data Index: 7740836 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4673. Min Act: -0.1700
Data Index: 723296 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4511. Min Act: -0.1700
Data Index: 5292491 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4348. Min Act: -0.1700
Data Index: 2338826 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4511. Min Act: -0.1700
Data Index: 2953942 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4511. Min Act: -0.1700
Data Index: 7003986 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4511. Min Act: -0.1700
Data Index: 2415743 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5321. Min Range: -2.5321
Max Act: 2.4348. Min Act: -0.1700
Data Index: 520152 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19