Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.7354. Min Act: -0.1700
Data Index: 1806813 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.5479. Min Act: -0.1700
Data Index: 8388120 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.3604. Min Act: -0.1700
Data Index: 830015 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.3604. Min Act: -0.1700
Data Index: 2144418 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.2354. Min Act: -0.1700
Data Index: 1155387 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.1729. Min Act: -0.1700
Data Index: 504176 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 8332478 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.1104. Min Act: -0.1700
Data Index: 7112573 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 6243849 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 6173540 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0479. Min Act: -0.1700
Data Index: 759874 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 6786724 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0792. Min Act: -0.1700
Data Index: 321996 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0167. Min Act: -0.1700
Data Index: 2124311 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0479. Min Act: -0.1700
Data Index: 7709857 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0479. Min Act: -0.1700
Data Index: 3927454 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0167. Min Act: -0.1700
Data Index: 4973508 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7354. Min Range: -7.7354
Max Act: 7.0167. Min Act: -0.1700
Data Index: 6186369 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7354. Min Range: -7.7354
Max Act: 6.9854. Min Act: -0.1700
Data Index: 6505042 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7354. Min Range: -7.7354
Max Act: 6.9542. Min Act: -0.1700
Data Index: 6680686 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19