Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1326. Min Range: -7.1326
Max Act: 7.1326. Min Act: -0.1700
Data Index: 6917403 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1326. Min Range: -7.1326
Max Act: 7.0389. Min Act: -0.1700
Data Index: 475887 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1326. Min Range: -7.1326
Max Act: 7.0076. Min Act: -0.1700
Data Index: 4067923 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1326. Min Range: -7.1326
Max Act: 7.0389. Min Act: -0.1700
Data Index: 617579 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.9764. Min Act: -0.1700
Data Index: 4860687 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.9764. Min Act: -0.1700
Data Index: 1618396 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.9764. Min Act: -0.1700
Data Index: 8465153 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8826. Min Act: -0.1700
Data Index: 3393904 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8826. Min Act: -0.1700
Data Index: 5459664 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8514. Min Act: -0.1700
Data Index: 200710 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8201. Min Act: -0.1700
Data Index: 368 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8201. Min Act: -0.1700
Data Index: 1979668 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.8201. Min Act: -0.1700
Data Index: 2957649 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7889. Min Act: -0.1700
Data Index: 118717 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7889. Min Act: -0.1700
Data Index: 5531585 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7889. Min Act: -0.1700
Data Index: 1992591 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7889. Min Act: -0.1700
Data Index: 8036207 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7576. Min Act: -0.1700
Data Index: 5088679 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7889. Min Act: -0.1700
Data Index: 3964393 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1326. Min Range: -7.1326
Max Act: 6.7576. Min Act: -0.1700
Data Index: 6574809 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19