Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7958. Min Act: -0.1700
Data Index: 4770173 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7645. Min Act: -0.1700
Data Index: 8503865 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4958167 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7645. Min Act: -0.1700
Data Index: 5630235 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7332. Min Act: -0.1700
Data Index: 3886854 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7332. Min Act: -0.1700
Data Index: 2881121 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7019. Min Act: -0.1700
Data Index: 7019876 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.7019. Min Act: -0.1700
Data Index: 4994621 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.6706. Min Act: -0.1700
Data Index: 6869507 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 3799176 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5767. Min Act: -0.1700
Data Index: 1639175 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5767. Min Act: -0.1700
Data Index: 6089037 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 7418089 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 1944723 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 7799024 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 1608133 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 4151910 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 7273780 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 4772877 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7958. Min Range: -3.7958
Max Act: 3.5454. Min Act: -0.1700
Data Index: 3915759 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19