Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5749 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.9054. Min Act: -0.1700
Data Index: 1554795 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.9054. Min Act: -0.1700
Data Index: 6220575 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.8429. Min Act: -0.1700
Data Index: 6525564 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.8429. Min Act: -0.1700
Data Index: 182846 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.7804. Min Act: -0.1700
Data Index: 5708736 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6242. Min Act: -0.1700
Data Index: 4188607 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.6242. Min Act: -0.1700
Data Index: 6882012 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5617. Min Act: -0.1700
Data Index: 242814 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.5304. Min Act: -0.1700
Data Index: 6135823 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 6950616 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 7799584 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4992. Min Act: -0.1700
Data Index: 3592400 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4367. Min Act: -0.1700
Data Index: 296032 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4679. Min Act: -0.1700
Data Index: 2748687 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4679. Min Act: -0.1700
Data Index: 6312345 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4367. Min Act: -0.1700
Data Index: 8190106 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4679. Min Act: -0.1700
Data Index: 843595 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4679. Min Act: -0.1700
Data Index: 1466666 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4367. Min Act: -0.1700
Data Index: 7635417 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9054. Min Range: -7.9054
Max Act: 7.4367. Min Act: -0.1700
Data Index: 7159892 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19