Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.0123. Min Range: -10.0123
Max Act: 10.0123. Min Act: -0.1700
Data Index: 3595576 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.9498. Min Act: -0.1700
Data Index: 2490610 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.9498. Min Act: -0.1700
Data Index: 2729976 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.8248. Min Act: -0.1700
Data Index: 2325063 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.8248. Min Act: -0.1700
Data Index: 6680152 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.8248. Min Act: -0.1700
Data Index: 2313750 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.7623. Min Act: -0.1700
Data Index: 2490611 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.6998. Min Act: -0.1700
Data Index: 2325062 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.6373. Min Act: -0.1700
Data Index: 8011146 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.6998. Min Act: -0.1700
Data Index: 6874247 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.6998. Min Act: -0.1700
Data Index: 6680135 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5748. Min Act: -0.1700
Data Index: 6680147 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5123. Min Act: -0.1700
Data Index: 6680149 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5748. Min Act: -0.1700
Data Index: 2490612 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5123. Min Act: -0.1700
Data Index: 5715651 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5123. Min Act: -0.1700
Data Index: 992145 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.4498. Min Act: -0.1700
Data Index: 4729838 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.5123. Min Act: -0.1700
Data Index: 3267197 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.4498. Min Act: -0.1700
Data Index: 6680142 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0123. Min Range: -10.0123
Max Act: 9.3873. Min Act: -0.1700
Data Index: 6680139 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19