Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4397 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1480. Min Range: -7.1480
Max Act: 7.1480. Min Act: -0.1700
Data Index: 1578524 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1480. Min Range: -7.1480
Max Act: 7.1167. Min Act: -0.1700
Data Index: 7448889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.8355. Min Act: -0.1700
Data Index: 6819277 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.7417. Min Act: -0.1700
Data Index: 3712847 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.7417. Min Act: -0.1699
Data Index: 3712848 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.7105. Min Act: -0.1700
Data Index: 1820560 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.6480. Min Act: -0.1700
Data Index: 7167619 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.6792. Min Act: -0.1700
Data Index: 3063225 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5855. Min Act: -0.1700
Data Index: 1009949 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.6167. Min Act: -0.1700
Data Index: 6911180 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.6167. Min Act: -0.1700
Data Index: 2109035 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5542. Min Act: -0.1700
Data Index: 1466866 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5542. Min Act: -0.1700
Data Index: 1228403 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5542. Min Act: -0.1700
Data Index: 3727233 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5230. Min Act: -0.1700
Data Index: 4534562 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.5230. Min Act: -0.1700
Data Index: 6901209 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.4917. Min Act: -0.1700
Data Index: 7269671 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.4605. Min Act: -0.1700
Data Index: 3427505 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.4605. Min Act: -0.1700
Data Index: 2748046 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1480. Min Range: -7.1480
Max Act: 6.4292. Min Act: -0.1700
Data Index: 6057930 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19