Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.4176. Min Act: -0.1700
Data Index: 8468822 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.3551. Min Act: -0.1700
Data Index: 2009690 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.3551. Min Act: -0.1700
Data Index: 1427732 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.2614. Min Act: -0.1700
Data Index: 866340 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.2926. Min Act: -0.1700
Data Index: 6206271 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1989. Min Act: -0.1700
Data Index: 2904571 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.2614. Min Act: -0.1700
Data Index: 5495872 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1989. Min Act: -0.1700
Data Index: 8294622 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1989. Min Act: -0.1700
Data Index: 291830 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 4004554 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1989. Min Act: -0.1700
Data Index: 60815 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 2046235 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 8417140 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1676. Min Act: -0.1700
Data Index: 5167004 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 3945869 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 2536720 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 1257389 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 4257472 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 6393356 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4176. Min Range: -5.4176
Max Act: 5.1364. Min Act: -0.1700
Data Index: 2261510 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19