Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3729. Min Range: -4.3729
Max Act: 4.3729. Min Act: -0.1700
Data Index: 8200653 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3729. Min Range: -4.3729
Max Act: 4.1541. Min Act: -0.1700
Data Index: 6040347 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3729. Min Range: -4.3729
Max Act: 4.1229. Min Act: -0.1700
Data Index: 7409929 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3729. Min Range: -4.3729
Max Act: 4.0291. Min Act: -0.1700
Data Index: 3850444 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9666. Min Act: -0.1700
Data Index: 2838593 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9666. Min Act: -0.1700
Data Index: 1530566 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9353. Min Act: -0.1700
Data Index: 2998862 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9041. Min Act: -0.1700
Data Index: 8400643 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9041. Min Act: -0.1700
Data Index: 5610716 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.9041. Min Act: -0.1700
Data Index: 6206709 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8728. Min Act: -0.1700
Data Index: 8626172 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8728. Min Act: -0.1700
Data Index: 5812792 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8415. Min Act: -0.1700
Data Index: 8626165 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8415. Min Act: -0.1700
Data Index: 2572474 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 1246975 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 8103763 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 7845892 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 8490587 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 2315560 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3729. Min Range: -4.3729
Max Act: 3.8102. Min Act: -0.1700
Data Index: 1621766 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19