Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.5876. Min Act: -0.1700
Data Index: 6543652 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.4001. Min Act: -0.1700
Data Index: 4104446 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.3688. Min Act: -0.1700
Data Index: 1582921 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.3063. Min Act: -0.1700
Data Index: 5272962 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.2126. Min Act: -0.1700
Data Index: 5410523 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.1813. Min Act: -0.1700
Data Index: 1497293 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.1813. Min Act: -0.1700
Data Index: 7223800 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.1813. Min Act: -0.1700
Data Index: 2549826 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0876. Min Act: -0.1700
Data Index: 3461124 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0876. Min Act: -0.1700
Data Index: 1247845 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0563. Min Act: -0.1700
Data Index: 8756588 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0563. Min Act: -0.1700
Data Index: 990551 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0563. Min Act: -0.1700
Data Index: 6154635 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0251. Min Act: -0.1700
Data Index: 8025447 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0251. Min Act: -0.1700
Data Index: 5879284 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0251. Min Act: -0.1700
Data Index: 454101 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5876. Min Range: -6.5876
Max Act: 6.0251. Min Act: -0.1700
Data Index: 7246046 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5876. Min Range: -6.5876
Max Act: 5.9938. Min Act: -0.1700
Data Index: 7580022 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5876. Min Range: -6.5876
Max Act: 5.9626. Min Act: -0.1700
Data Index: 607658 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5876. Min Range: -6.5876
Max Act: 5.9938. Min Act: -0.1700
Data Index: 2026242 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19