Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 7231572 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3732. Min Act: -0.1700
Data Index: 5162474 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3732. Min Act: -0.1700
Data Index: 7377609 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3732. Min Act: -0.1700
Data Index: 2026812 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3420. Min Act: -0.1700
Data Index: 7377608 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3420. Min Act: -0.1700
Data Index: 8404643 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 467332 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 2110770 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2170. Min Act: -0.1700
Data Index: 142269 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2170. Min Act: -0.1700
Data Index: 324529 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 4398057 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2170. Min Act: -0.1700
Data Index: 2179806 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 6575640 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 1042653 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 6391360 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 4164351 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2685186 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1545. Min Act: -0.1700
Data Index: 3342630 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1857. Min Act: -0.1700
Data Index: 6963686 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.1545. Min Act: -0.1700
Data Index: 3601823 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19