Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1566 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.5605. Min Act: -0.1700
Data Index: 8281178 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.5448. Min Act: -0.1700
Data Index: 4551788 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.5448. Min Act: -0.1700
Data Index: 7430132 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4978. Min Act: -0.1700
Data Index: 5195925 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4978. Min Act: -0.1700
Data Index: 2662208 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4978. Min Act: -0.1700
Data Index: 4501748 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4822. Min Act: -0.1700
Data Index: 1586348 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4665. Min Act: -0.1700
Data Index: 2683466 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4508. Min Act: -0.1700
Data Index: 1384506 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4038. Min Act: -0.1700
Data Index: 598220 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4038. Min Act: -0.1700
Data Index: 6196634 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4195. Min Act: -0.1700
Data Index: 6984709 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4038. Min Act: -0.1700
Data Index: 1030060 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3881. Min Act: -0.1700
Data Index: 6606966 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3881. Min Act: -0.1700
Data Index: 410449 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3568. Min Act: -0.1700
Data Index: 2587860 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3881. Min Act: -0.1700
Data Index: 1626607 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.4038. Min Act: -0.1700
Data Index: 8281097 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3568. Min Act: -0.1700
Data Index: 2637071 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5605. Min Range: -3.5605
Max Act: 3.3881. Min Act: -0.1700
Data Index: 4657611 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19