Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.5977. Min Act: -0.1700
Data Index: 3916996 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.4727. Min Act: -0.1700
Data Index: 1811729 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.5039. Min Act: -0.1700
Data Index: 3773763 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.5352. Min Act: -0.1700
Data Index: 1380997 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.4414. Min Act: -0.1700
Data Index: 5635299 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.4414. Min Act: -0.1700
Data Index: 819145 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.4414. Min Act: -0.1700
Data Index: 8274367 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.3164. Min Act: -0.1700
Data Index: 1688600 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.3477. Min Act: -0.1700
Data Index: 1983645 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.3477. Min Act: -0.1700
Data Index: 8145772 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.3477. Min Act: -0.1700
Data Index: 1727908 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.3164. Min Act: -0.1700
Data Index: 4693935 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2852. Min Act: -0.1700
Data Index: 6238300 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2539. Min Act: -0.1700
Data Index: 3550607 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2539. Min Act: -0.1700
Data Index: 7667012 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2539. Min Act: -0.1700
Data Index: 8560787 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2539. Min Act: -0.1700
Data Index: 2978748 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2539. Min Act: -0.1700
Data Index: 8277988 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.2227. Min Act: -0.1700
Data Index: 413814 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5977. Min Range: -5.5977
Max Act: 5.1914. Min Act: -0.1700
Data Index: 2527155 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19