Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.3112. Min Act: -0.1700
Data Index: 1436665 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2798. Min Act: -0.1700
Data Index: 7517990 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2641. Min Act: -0.1700
Data Index: 8790091 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2327. Min Act: -0.1700
Data Index: 3035838 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2170. Min Act: -0.1700
Data Index: 4827756 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2012. Min Act: -0.1700
Data Index: 239584 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1855. Min Act: -0.1700
Data Index: 7582567 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2170. Min Act: -0.1700
Data Index: 4089855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2012. Min Act: -0.1700
Data Index: 7258251 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.2012. Min Act: -0.1700
Data Index: 4009707 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1855. Min Act: -0.1700
Data Index: 4597337 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1855. Min Act: -0.1700
Data Index: 7194478 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1698. Min Act: -0.1700
Data Index: 219032 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1698. Min Act: -0.1700
Data Index: 7517993 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1540. Min Act: -0.1700
Data Index: 5041731 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1855. Min Act: -0.1700
Data Index: 8209867 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1540. Min Act: -0.1700
Data Index: 7950479 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1540. Min Act: -0.1700
Data Index: 6729850 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1383. Min Act: -0.1700
Data Index: 2142560 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3112. Min Range: -3.3112
Max Act: 3.1225. Min Act: -0.1700
Data Index: 4075041 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19