Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4676 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5336. Min Range: -7.5336
Max Act: 7.5336. Min Act: -0.1700
Data Index: 6561623 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5336. Min Range: -7.5336
Max Act: 7.1898. Min Act: -0.1700
Data Index: 3200983 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5336. Min Range: -7.5336
Max Act: 7.0648. Min Act: -0.1700
Data Index: 3200986 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5336. Min Range: -7.5336
Max Act: 7.0023. Min Act: -0.1700
Data Index: 7906756 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.9398. Min Act: -0.1700
Data Index: 4907166 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.9398. Min Act: -0.1700
Data Index: 2932381 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8461. Min Act: -0.1700
Data Index: 8071765 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8461. Min Act: -0.1700
Data Index: 1738018 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8773. Min Act: -0.1700
Data Index: 427851 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8461. Min Act: -0.1700
Data Index: 2932382 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8461. Min Act: -0.1700
Data Index: 2437175 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 348395 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8148. Min Act: -0.1700
Data Index: 1233048 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.8148. Min Act: -0.1700
Data Index: 8597720 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 2505255 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 7966010 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 6166626 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 1395145 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 5139786 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5336. Min Range: -7.5336
Max Act: 6.7836. Min Act: -0.1700
Data Index: 4216580 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19