Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.8399. Min Act: -0.1700
Data Index: 5000180 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.7774. Min Act: -0.1700
Data Index: 163462 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.7462. Min Act: -0.1700
Data Index: 3473187 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.7149. Min Act: -0.1700
Data Index: 1290001 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.7149. Min Act: -0.1700
Data Index: 3265250 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.6524. Min Act: -0.1700
Data Index: 7770481 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.6212. Min Act: -0.1700
Data Index: 20947 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.5587. Min Act: -0.1700
Data Index: 4321449 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.5899. Min Act: -0.1700
Data Index: 6224308 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.5587. Min Act: -0.1700
Data Index: 452833 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.5274. Min Act: -0.1700
Data Index: 4553152 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4962. Min Act: -0.1700
Data Index: 1677492 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2259552 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1518295 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4649. Min Act: -0.1700
Data Index: 1298529 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4337. Min Act: -0.1700
Data Index: 477670 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4337. Min Act: -0.1700
Data Index: 6952883 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4337. Min Act: -0.1700
Data Index: 2385510 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4649. Min Act: -0.1700
Data Index: 7584660 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8399. Min Range: -5.8399
Max Act: 5.4024. Min Act: -0.1700
Data Index: 6337388 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19