Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.3725. Min Act: -0.1700
Data Index: 7278827 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.3412. Min Act: -0.1700
Data Index: 4704856 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2475. Min Act: -0.1700
Data Index: 1960608 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2475. Min Act: -0.1700
Data Index: 3387030 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2787. Min Act: -0.1700
Data Index: 5870878 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2787. Min Act: -0.1700
Data Index: 3292740 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2162. Min Act: -0.1700
Data Index: 5743271 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.2475. Min Act: -0.1700
Data Index: 8252422 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1850. Min Act: -0.1700
Data Index: 4755870 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1850. Min Act: -0.1700
Data Index: 8823407 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1850. Min Act: -0.1700
Data Index: 3736232 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1850. Min Act: -0.1700
Data Index: 1231326 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1225. Min Act: -0.1700
Data Index: 8192250 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 7763686 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 809080 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 5777415 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 1534059 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 8798126 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1537. Min Act: -0.1700
Data Index: 7045923 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3725. Min Range: -4.3725
Max Act: 4.1225. Min Act: -0.1700
Data Index: 5121549 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19