Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0704. Min Range: -6.0704
Max Act: 6.0704. Min Act: -0.1700
Data Index: 1687094 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.9454. Min Act: -0.1700
Data Index: 8151936 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.9767. Min Act: -0.1700
Data Index: 1082958 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.9454. Min Act: -0.1700
Data Index: 8629599 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8829. Min Act: -0.1700
Data Index: 545019 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.9142. Min Act: -0.1700
Data Index: 1011569 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8204. Min Act: -0.1700
Data Index: 5271423 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8517. Min Act: -0.1700
Data Index: 4340343 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8517. Min Act: -0.1700
Data Index: 6275076 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7892. Min Act: -0.1700
Data Index: 130499 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8204. Min Act: -0.1700
Data Index: 2307760 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8204. Min Act: -0.1700
Data Index: 5718622 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8517. Min Act: -0.1700
Data Index: 751561 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7892. Min Act: -0.1700
Data Index: 5178874 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7579. Min Act: -0.1700
Data Index: 4607995 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.8204. Min Act: -0.1700
Data Index: 577618 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7579. Min Act: -0.1700
Data Index: 1301952 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7892. Min Act: -0.1700
Data Index: 1938745 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7579. Min Act: -0.1700
Data Index: 779844 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0704. Min Range: -6.0704
Max Act: 5.7892. Min Act: -0.1700
Data Index: 2366671 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19