Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 427 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.9665. Min Act: -0.1700
Data Index: 6756134 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.9353. Min Act: -0.1700
Data Index: 475404 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.8728. Min Act: -0.1700
Data Index: 8694988 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.8103. Min Act: -0.1700
Data Index: 455879 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.7165. Min Act: -0.1700
Data Index: 4823252 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.6228. Min Act: -0.1700
Data Index: 4309692 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2390468 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.5603. Min Act: -0.1700
Data Index: 2700811 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4978. Min Act: -0.1700
Data Index: 7816777 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4978. Min Act: -0.1700
Data Index: 2177426 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4665. Min Act: -0.1700
Data Index: 3557691 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4353. Min Act: -0.1700
Data Index: 8443617 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4353. Min Act: -0.1700
Data Index: 8059653 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4353. Min Act: -0.1700
Data Index: 7758847 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.4040. Min Act: -0.1700
Data Index: 6316809 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.3728. Min Act: -0.1700
Data Index: 8232716 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.3415. Min Act: -0.1700
Data Index: 4703289 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.3728. Min Act: -0.1700
Data Index: 5720231 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.3103. Min Act: -0.1700
Data Index: 2104504 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9665. Min Range: -6.9665
Max Act: 6.2790. Min Act: -0.1700
Data Index: 1397312 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19