Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 6682879 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9469. Min Act: -0.1700
Data Index: 3193099 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 6535556 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 238380 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 3262984 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 5929185 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.9152. Min Act: -0.1700
Data Index: 3745804 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 5763432 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 5520705 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 1698135 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 20755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 1210494 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 2377120 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 4912443 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 1854799 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 6535558 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 1948094 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 4854784 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 6656774 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9469. Min Range: -2.9469
Max Act: 2.8835. Min Act: -0.1700
Data Index: 2058144 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19