Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1686784 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7363. Min Act: -0.1700
Data Index: 3027141 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7363. Min Act: -0.1700
Data Index: 7754941 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2570722 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7051. Min Act: -0.1700
Data Index: 1971369 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7051. Min Act: -0.1700
Data Index: 1776923 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6738. Min Act: -0.1700
Data Index: 587525 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6738. Min Act: -0.1700
Data Index: 6329841 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6426. Min Act: -0.1700
Data Index: 634127 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 172015 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 1460302 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 8559060 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 8664034 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 1212520 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 3842710 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 8269148 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4730775 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7514343 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 3249295 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5488. Min Act: -0.1700
Data Index: 6106831 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19