Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.5821. Min Act: -0.1700
Data Index: 8291328 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.4883. Min Act: -0.1700
Data Index: 3496495 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.4883. Min Act: -0.1700
Data Index: 5400906 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.4883. Min Act: -0.1700
Data Index: 2139336 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.3946. Min Act: -0.1700
Data Index: 7955999 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.3633. Min Act: -0.1700
Data Index: 5711808 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.3321. Min Act: -0.1700
Data Index: 4195346 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.3008. Min Act: -0.1700
Data Index: 5827633 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2696. Min Act: -0.1700
Data Index: 2668602 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2696. Min Act: -0.1700
Data Index: 1638782 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2383. Min Act: -0.1700
Data Index: 8307867 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2383. Min Act: -0.1700
Data Index: 4636724 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2383. Min Act: -0.1700
Data Index: 7581165 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3338572 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2071. Min Act: -0.1700
Data Index: 8814768 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.2071. Min Act: -0.1700
Data Index: 1737178 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.1758. Min Act: -0.1700
Data Index: 5705902 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.1758. Min Act: -0.1700
Data Index: 4428118 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.1446. Min Act: -0.1700
Data Index: 6630001 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5821. Min Range: -6.5821
Max Act: 6.1133. Min Act: -0.1700
Data Index: 4951980 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19