Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5945 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.8404. Min Act: -0.1700
Data Index: 5729925 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.4029. Min Act: -0.1700
Data Index: 2565189 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.3404. Min Act: -0.1700
Data Index: 6281013 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.2779. Min Act: -0.1700
Data Index: 3567271 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.2154. Min Act: -0.1700
Data Index: 5944 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.2779. Min Act: -0.1700
Data Index: 5153206 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.2154. Min Act: -0.1700
Data Index: 7846773 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.2154. Min Act: -0.1700
Data Index: 5752056 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.1529. Min Act: -0.1700
Data Index: 2254681 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.1529. Min Act: -0.1700
Data Index: 2543827 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 2585698 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 1835992 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 5555938 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 3016062 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 7144111 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0904. Min Act: -0.1700
Data Index: 5624086 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0279. Min Act: -0.1700
Data Index: 2624799 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8404. Min Range: -8.8404
Max Act: 8.0279. Min Act: -0.1700
Data Index: 3904986 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8404. Min Range: -8.8404
Max Act: 7.9654. Min Act: -0.1700
Data Index: 5909095 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8404. Min Range: -8.8404
Max Act: 7.9654. Min Act: -0.1700
Data Index: 4248866 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19