Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 850 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.8918. Min Act: -0.1700
Data Index: 3165340 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.6731. Min Act: -0.1700
Data Index: 2581937 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.6418. Min Act: -0.1700
Data Index: 1717687 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.5793. Min Act: -0.1700
Data Index: 4013503 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.5793. Min Act: -0.1700
Data Index: 1894610 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.5481. Min Act: -0.1700
Data Index: 5979298 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.5793. Min Act: -0.1700
Data Index: 8197280 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4856. Min Act: -0.1700
Data Index: 4093180 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4543. Min Act: -0.1700
Data Index: 577138 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4856. Min Act: -0.1700
Data Index: 1031707 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4543. Min Act: -0.1700
Data Index: 861058 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4543. Min Act: -0.1700
Data Index: 8157158 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4543. Min Act: -0.1700
Data Index: 7124500 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4231. Min Act: -0.1700
Data Index: 8368656 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 3096867 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.3606. Min Act: -0.1700
Data Index: 8422603 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.4231. Min Act: -0.1700
Data Index: 8061976 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 1829793 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 6458190 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8918. Min Range: -6.8918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 5728754 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19