Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2780. Min Range: -6.2780
Max Act: 6.2780. Min Act: -0.1700
Data Index: 6467779 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.9030. Min Act: -0.1700
Data Index: 7142349 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.6530. Min Act: -0.1700
Data Index: 2999285 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.6217. Min Act: -0.1700
Data Index: 8728102 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.5905. Min Act: -0.1700
Data Index: 6397891 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.5592. Min Act: -0.1700
Data Index: 679757 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.5280. Min Act: -0.1700
Data Index: 7791498 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4655. Min Act: -0.1700
Data Index: 2884001 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4655. Min Act: -0.1700
Data Index: 2883999 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4655. Min Act: -0.1700
Data Index: 4155476 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4030. Min Act: -0.1700
Data Index: 2884004 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4030. Min Act: -0.1700
Data Index: 1988060 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4342. Min Act: -0.1700
Data Index: 8772787 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4030. Min Act: -0.1700
Data Index: 7135600 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4342. Min Act: -0.1700
Data Index: 5966896 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.3405. Min Act: -0.1700
Data Index: 196893 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.4030. Min Act: -0.1700
Data Index: 3031271 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.3405. Min Act: -0.1700
Data Index: 1802401 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.3405. Min Act: -0.1700
Data Index: 5014857 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2780. Min Range: -6.2780
Max Act: 5.3405. Min Act: -0.1700
Data Index: 6027988 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19