Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1561 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.1803. Min Range: -14.1803
Max Act: 14.1803. Min Act: -0.1700
Data Index: 5286385 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.9928. Min Act: -0.1700
Data Index: 8466752 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.9928. Min Act: -0.1700
Data Index: 3929098 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.9303. Min Act: -0.1700
Data Index: 5082251 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.7428. Min Act: -0.1700
Data Index: 4099737 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.7428. Min Act: -0.1700
Data Index: 6084850 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.7428. Min Act: -0.1700
Data Index: 4705550 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6803. Min Act: -0.1700
Data Index: 1848114 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6803. Min Act: -0.1700
Data Index: 2899652 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 4158024 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6803. Min Act: -0.1700
Data Index: 8024449 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6803. Min Act: -0.1700
Data Index: 8747578 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6803. Min Act: -0.1700
Data Index: 6904613 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 7069316 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 2305972 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 7207070 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 6541288 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.6178. Min Act: -0.1700
Data Index: 5049186 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.5553. Min Act: -0.1700
Data Index: 7926907 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1803. Min Range: -14.1803
Max Act: 13.4928. Min Act: -0.1700
Data Index: 2540499 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19