Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.5053. Min Act: -0.1700
Data Index: 354800 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.3178. Min Act: -0.1700
Data Index: 4798087 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.3178. Min Act: -0.1700
Data Index: 8257240 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.2553. Min Act: -0.1700
Data Index: 3106721 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1928. Min Act: -0.1700
Data Index: 8649495 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1303. Min Act: -0.1700
Data Index: 2356724 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1303. Min Act: -0.1700
Data Index: 811330 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1303. Min Act: -0.1700
Data Index: 7609845 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1303. Min Act: -0.1700
Data Index: 5058978 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.1303. Min Act: -0.1700
Data Index: 399432 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0678. Min Act: -0.1700
Data Index: 474414 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0678. Min Act: -0.1700
Data Index: 6762126 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0678. Min Act: -0.1700
Data Index: 6207471 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0678. Min Act: -0.1700
Data Index: 7853591 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0053. Min Act: -0.1700
Data Index: 7614720 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0053. Min Act: -0.1700
Data Index: 8057725 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5053. Min Range: -8.5053
Max Act: 8.0053. Min Act: -0.1700
Data Index: 1257172 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5053. Min Range: -8.5053
Max Act: 7.9428. Min Act: -0.1700
Data Index: 2717963 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5053. Min Range: -8.5053
Max Act: 7.9428. Min Act: -0.1700
Data Index: 6640895 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5053. Min Range: -8.5053
Max Act: 7.9428. Min Act: -0.1700
Data Index: 7151151 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19