Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.9933. Min Act: -0.1700
Data Index: 8098412 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.8058. Min Act: -0.1700
Data Index: 4538906 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.4933. Min Act: -0.1700
Data Index: 5915850 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.4308. Min Act: -0.1700
Data Index: 4163496 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.2433. Min Act: -0.1700
Data Index: 5681659 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.2433. Min Act: -0.1700
Data Index: 4888223 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 8201773 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 8428497 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 6348695 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 6649813 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 4582309 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1808. Min Act: -0.1700
Data Index: 7310582 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1183. Min Act: -0.1700
Data Index: 6051716 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1183. Min Act: -0.1700
Data Index: 8342417 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1183. Min Act: -0.1700
Data Index: 3897611 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1183. Min Act: -0.1700
Data Index: 3581403 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.1183. Min Act: -0.1700
Data Index: 5241289 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.0558. Min Act: -0.1700
Data Index: 3873928 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.0558. Min Act: -0.1700
Data Index: 5302046 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9933. Min Range: -8.9933
Max Act: 8.0558. Min Act: -0.1700
Data Index: 725769 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19