Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.9359. Min Act: -0.1700
Data Index: 4381005 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.9046. Min Act: -0.1700
Data Index: 1458760 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.9359. Min Act: -0.1700
Data Index: 4750158 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.9046. Min Act: -0.1700
Data Index: 2747340 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.8421. Min Act: -0.1700
Data Index: 1791934 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.8109. Min Act: -0.1700
Data Index: 2471433 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.8109. Min Act: -0.1700
Data Index: 155012 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.7796. Min Act: -0.1700
Data Index: 5578665 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.7796. Min Act: -0.1700
Data Index: 5770525 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6859. Min Act: -0.1700
Data Index: 4967296 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6859. Min Act: -0.1700
Data Index: 8095977 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.7171. Min Act: -0.1700
Data Index: 5435812 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.7171. Min Act: -0.1700
Data Index: 3197450 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6859. Min Act: -0.1700
Data Index: 2462755 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6546. Min Act: -0.1700
Data Index: 3865113 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6546. Min Act: -0.1700
Data Index: 535569 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6234. Min Act: -0.1700
Data Index: 2410014 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.6546. Min Act: -0.1700
Data Index: 8207835 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.5921. Min Act: -0.1700
Data Index: 5870210 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9359. Min Range: -7.9359
Max Act: 7.5921. Min Act: -0.1700
Data Index: 4223756 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19