Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.5938. Min Act: -0.1700
Data Index: 6094557 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.5938. Min Act: -0.1700
Data Index: 4676532 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.5313. Min Act: -0.1700
Data Index: 2902630 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.5313. Min Act: -0.1700
Data Index: 4625534 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.5313. Min Act: -0.1700
Data Index: 4477427 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.4063. Min Act: -0.1700
Data Index: 1435731 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.3438. Min Act: -0.1700
Data Index: 1482107 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.2813. Min Act: -0.1700
Data Index: 6606540 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.3438. Min Act: -0.1700
Data Index: 4293488 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.2188. Min Act: -0.1700
Data Index: 377980 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.1563. Min Act: -0.1700
Data Index: 1845838 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.1563. Min Act: -0.1700
Data Index: 377981 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.1563. Min Act: -0.1700
Data Index: 377982 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.1563. Min Act: -0.1700
Data Index: 6150899 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.0938. Min Act: -0.1700
Data Index: 5915645 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.0313. Min Act: -0.1700
Data Index: 4853473 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5938. Min Range: -9.5938
Max Act: 9.0313. Min Act: -0.1700
Data Index: 359421 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5938. Min Range: -9.5938
Max Act: 8.9688. Min Act: -0.1700
Data Index: 3176253 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5938. Min Range: -9.5938
Max Act: 8.9688. Min Act: -0.1700
Data Index: 5498643 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5938. Min Range: -9.5938
Max Act: 8.9688. Min Act: -0.1700
Data Index: 5926912 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19