Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4989 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.2721. Min Act: -0.1700
Data Index: 3265300 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.1784. Min Act: -0.1700
Data Index: 4971856 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.0846. Min Act: -0.1700
Data Index: 4056370 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.0534. Min Act: -0.1700
Data Index: 7854796 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.9596. Min Act: -0.1700
Data Index: 703774 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8971. Min Act: -0.1700
Data Index: 1767967 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8659. Min Act: -0.1700
Data Index: 7514949 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8346. Min Act: -0.1700
Data Index: 5644358 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8659. Min Act: -0.1700
Data Index: 4544949 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8034. Min Act: -0.1700
Data Index: 1646911 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7850105 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 4106606 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 5217001 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7409. Min Act: -0.1700
Data Index: 899388 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4057749 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 6485471 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7409. Min Act: -0.1700
Data Index: 5194922 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.6784. Min Act: -0.1700
Data Index: 8333649 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7096. Min Act: -0.1700
Data Index: 438358 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7096. Min Act: -0.1700
Data Index: 7622871 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19