Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 349 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1601. Min Range: -10.1601
Max Act: 10.1601. Min Act: -0.1700
Data Index: 5704985 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.2226. Min Act: -0.1700
Data Index: 62515 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.2226. Min Act: -0.1700
Data Index: 1845388 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.1601. Min Act: -0.1700
Data Index: 5501624 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.1601. Min Act: -0.1700
Data Index: 7925520 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.0351. Min Act: -0.1700
Data Index: 881708 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1601. Min Range: -10.1601
Max Act: 9.0351. Min Act: -0.1700
Data Index: 2232696 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9726. Min Act: -0.1700
Data Index: 5819874 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9726. Min Act: -0.1700
Data Index: 4288031 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9101. Min Act: -0.1700
Data Index: 4131657 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9101. Min Act: -0.1700
Data Index: 2815867 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9101. Min Act: -0.1700
Data Index: 8291723 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.9101. Min Act: -0.1700
Data Index: 1521078 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.8476. Min Act: -0.1700
Data Index: 1607507 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.8476. Min Act: -0.1700
Data Index: 2438272 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.8476. Min Act: -0.1700
Data Index: 2519868 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.7851. Min Act: -0.1700
Data Index: 2934148 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.7851. Min Act: -0.1700
Data Index: 4512831 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.7851. Min Act: -0.1700
Data Index: 6827160 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1601. Min Range: -10.1601
Max Act: 8.8476. Min Act: -0.1700
Data Index: 12622 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19