Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0524. Min Range: -6.0524
Max Act: 6.0524. Min Act: -0.1700
Data Index: 5764023 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0524. Min Range: -6.0524
Max Act: 6.0212. Min Act: -0.1700
Data Index: 3390740 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9899. Min Act: -0.1700
Data Index: 4309526 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9899. Min Act: -0.1700
Data Index: 8022346 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9587. Min Act: -0.1700
Data Index: 2475870 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9587. Min Act: -0.1700
Data Index: 2080647 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9274. Min Act: -0.1700
Data Index: 7348037 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9587. Min Act: -0.1700
Data Index: 6580354 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9899. Min Act: -0.1700
Data Index: 2080645 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9274. Min Act: -0.1700
Data Index: 5012729 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9274. Min Act: -0.1700
Data Index: 6118424 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9274. Min Act: -0.1700
Data Index: 3795827 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.9274. Min Act: -0.1700
Data Index: 2295598 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3594776 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3126367 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8649. Min Act: -0.1700
Data Index: 6612017 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8649. Min Act: -0.1700
Data Index: 6850781 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8649. Min Act: -0.1700
Data Index: 3080771 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8337. Min Act: -0.1700
Data Index: 4976397 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0524. Min Range: -6.0524
Max Act: 5.8337. Min Act: -0.1700
Data Index: 4227884 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19