Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1820. Min Act: -0.1700
Data Index: 7939426 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1820. Min Act: -0.1700
Data Index: 3855784 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1820. Min Act: -0.1700
Data Index: 2371944 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1505. Min Act: -0.1700
Data Index: 8316007 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1505. Min Act: -0.1700
Data Index: 2192528 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1347. Min Act: -0.1700
Data Index: 3054459 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1190. Min Act: -0.1700
Data Index: 8183681 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1190. Min Act: -0.1700
Data Index: 6875671 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1032. Min Act: -0.1700
Data Index: 7213453 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1032. Min Act: -0.1700
Data Index: 5040307 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.1032. Min Act: -0.1700
Data Index: 4430826 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0717. Min Act: -0.1700
Data Index: 1601979 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0875. Min Act: -0.1700
Data Index: 1221393 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0875. Min Act: -0.1700
Data Index: 7668345 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0875. Min Act: -0.1700
Data Index: 3038832 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0875. Min Act: -0.1700
Data Index: 5308042 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0717. Min Act: -0.1700
Data Index: 5449935 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0717. Min Act: -0.1700
Data Index: 7508014 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0717. Min Act: -0.1700
Data Index: 1042608 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1820. Min Range: -3.1820
Max Act: 3.0717. Min Act: -0.1700
Data Index: 8154812 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19