Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.6346. Min Act: -0.1700
Data Index: 781988 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.1659. Min Act: -0.1700
Data Index: 1044565 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.1659. Min Act: -0.1700
Data Index: 1459916 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.1034. Min Act: -0.1700
Data Index: 639458 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.0409. Min Act: -0.1700
Data Index: 4132621 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.0721. Min Act: -0.1700
Data Index: 1756426 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.0409. Min Act: -0.1700
Data Index: 1943281 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.0096. Min Act: -0.1700
Data Index: 7269286 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6346. Min Range: -7.6346
Max Act: 7.0096. Min Act: -0.1700
Data Index: 3538151 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.9784. Min Act: -0.1700
Data Index: 5081719 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.9471. Min Act: -0.1700
Data Index: 8529054 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8846. Min Act: -0.1700
Data Index: 2764234 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8846. Min Act: -0.1700
Data Index: 5789032 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8534. Min Act: -0.1700
Data Index: 4789854 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8534. Min Act: -0.1700
Data Index: 212224 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8221. Min Act: -0.1700
Data Index: 5270913 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8221. Min Act: -0.1700
Data Index: 265140 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8221. Min Act: -0.1700
Data Index: 4881162 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8221. Min Act: -0.1700
Data Index: 4537739 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6346. Min Range: -7.6346
Max Act: 6.8221. Min Act: -0.1700
Data Index: 5516275 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19