Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 381 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.3876. Min Act: -0.1700
Data Index: 1797097 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.3251. Min Act: -0.1700
Data Index: 669566 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.3251. Min Act: -0.1700
Data Index: 6595394 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.2626. Min Act: -0.1700
Data Index: 5926148 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.2001. Min Act: -0.1700
Data Index: 587976 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.2001. Min Act: -0.1700
Data Index: 4858914 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.2001. Min Act: -0.1700
Data Index: 6660093 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.2001. Min Act: -0.1700
Data Index: 1669642 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.1376. Min Act: -0.1700
Data Index: 7218099 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.1376. Min Act: -0.1700
Data Index: 7155418 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.1376. Min Act: -0.1700
Data Index: 6266144 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 6906521 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 5547998 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 3751833 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 2756594 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 5909771 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 1252853 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 7445862 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 5594995 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3876. Min Range: -8.3876
Max Act: 8.0751. Min Act: -0.1700
Data Index: 6717834 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19