Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.7441. Min Act: -0.1700
Data Index: 6175100 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.7282. Min Act: -0.1700
Data Index: 5895610 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.7122. Min Act: -0.1700
Data Index: 5163070 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6802. Min Act: -0.1700
Data Index: 2857561 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6962. Min Act: -0.1700
Data Index: 6810910 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6802. Min Act: -0.1700
Data Index: 8527228 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6641. Min Act: -0.1700
Data Index: 6273322 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6481. Min Act: -0.1700
Data Index: 5585943 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6481. Min Act: -0.1700
Data Index: 1522016 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.6160. Min Act: -0.1700
Data Index: 7939596 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5838. Min Act: -0.1700
Data Index: 5584356 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5838. Min Act: -0.1700
Data Index: 4230786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5677. Min Act: -0.1700
Data Index: 7873093 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5677. Min Act: -0.1700
Data Index: 5695159 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5677. Min Act: -0.1700
Data Index: 2440410 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5677. Min Act: -0.1700
Data Index: 3850206 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5354. Min Act: -0.1700
Data Index: 4770462 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5515. Min Act: -0.1700
Data Index: 790636 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5354. Min Act: -0.1700
Data Index: 8240635 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7441. Min Range: -2.7441
Max Act: 2.5515. Min Act: -0.1700
Data Index: 863680 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19