Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3589. Min Range: -6.3589
Max Act: 6.3589. Min Act: -0.1700
Data Index: 1202686 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3589. Min Range: -6.3589
Max Act: 6.1714. Min Act: -0.1700
Data Index: 1131375 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3589. Min Range: -6.3589
Max Act: 6.0776. Min Act: -0.1700
Data Index: 638365 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3589. Min Range: -6.3589
Max Act: 6.0151. Min Act: -0.1700
Data Index: 255735 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3589. Min Range: -6.3589
Max Act: 6.0151. Min Act: -0.1700
Data Index: 112013 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9526. Min Act: -0.1700
Data Index: 4563317 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9839. Min Act: -0.1700
Data Index: 4040349 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9839. Min Act: -0.1700
Data Index: 2183963 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9839. Min Act: -0.1700
Data Index: 2911486 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9526. Min Act: -0.1700
Data Index: 8374348 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9526. Min Act: -0.1700
Data Index: 4973207 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9214. Min Act: -0.1700
Data Index: 2872131 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9214. Min Act: -0.1700
Data Index: 325101 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9214. Min Act: -0.1700
Data Index: 4413446 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9214. Min Act: -0.1700
Data Index: 478788 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.9214. Min Act: -0.1700
Data Index: 8202017 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.8901. Min Act: -0.1700
Data Index: 821461 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.8901. Min Act: -0.1700
Data Index: 6309352 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.7964. Min Act: -0.1700
Data Index: 112010 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3589. Min Range: -6.3589
Max Act: 5.8276. Min Act: -0.1700
Data Index: 6446809 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19