Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4217. Min Range: -8.4217
Max Act: 8.4217. Min Act: -0.1700
Data Index: 2502812 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4217. Min Range: -8.4217
Max Act: 8.3592. Min Act: -0.1700
Data Index: 1597441 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4217. Min Range: -8.4217
Max Act: 8.1717. Min Act: -0.1700
Data Index: 969462 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4217. Min Range: -8.4217
Max Act: 8.1092. Min Act: -0.1700
Data Index: 8505767 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4217. Min Range: -8.4217
Max Act: 8.1092. Min Act: -0.1700
Data Index: 6036049 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.9842. Min Act: -0.1700
Data Index: 4737780 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.8592. Min Act: -0.1700
Data Index: 7756885 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.9217. Min Act: -0.1700
Data Index: 7838777 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.9217. Min Act: -0.1700
Data Index: 5140608 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.9217. Min Act: -0.1700
Data Index: 7912984 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.8592. Min Act: -0.1700
Data Index: 6871126 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.8592. Min Act: -0.1700
Data Index: 6911037 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 3098668 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 2787754 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 799794 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 4448921 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 7616393 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7967. Min Act: -0.1700
Data Index: 7393989 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.8592. Min Act: -0.1700
Data Index: 3288794 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4217. Min Range: -8.4217
Max Act: 7.7342. Min Act: -0.1700
Data Index: 3135999 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19