Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2521 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.5132. Min Act: -0.1700
Data Index: 5000077 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.3882. Min Act: -0.1700
Data Index: 2003604 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.3882. Min Act: -0.1700
Data Index: 5457464 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.1382. Min Act: -0.1700
Data Index: 4487537 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.0132. Min Act: -0.1700
Data Index: 2013372 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.1382. Min Act: -0.1700
Data Index: 3991158 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.2632. Min Act: -0.1700
Data Index: 1410334 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.0132. Min Act: -0.1700
Data Index: 8035896 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.5132. Min Range: -16.5132
Max Act: 16.0132. Min Act: -0.1700
Data Index: 8580371 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.8882. Min Act: -0.1700
Data Index: 1775066 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.8882. Min Act: -0.1700
Data Index: 5363573 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.7632. Min Act: -0.1700
Data Index: 5493964 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.7632. Min Act: -0.1700
Data Index: 5389442 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.7632. Min Act: -0.1699
Data Index: 2225535 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.7632. Min Act: -0.1700
Data Index: 3801864 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.6382. Min Act: -0.1700
Data Index: 1907452 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.6382. Min Act: -0.1700
Data Index: 4122301 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.6382. Min Act: -0.1700
Data Index: 5316246 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.6382. Min Act: -0.1700
Data Index: 3004604 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.5132. Min Range: -16.5132
Max Act: 15.5132. Min Act: -0.1700
Data Index: 2467878 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19