Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5598 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1492. Min Range: -6.1492
Max Act: 6.1492. Min Act: -0.1700
Data Index: 674767 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.8992. Min Act: -0.1700
Data Index: 859278 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.8055. Min Act: -0.1700
Data Index: 8406166 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.7742. Min Act: -0.1700
Data Index: 693934 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7346278 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.7430. Min Act: -0.1700
Data Index: 6616768 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.6805. Min Act: -0.1700
Data Index: 2816783 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.6805. Min Act: -0.1700
Data Index: 3124729 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.6492. Min Act: -0.1700
Data Index: 5665869 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.6492. Min Act: -0.1700
Data Index: 6749824 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5140214 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5013489 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4930. Min Act: -0.1700
Data Index: 828617 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4930. Min Act: -0.1700
Data Index: 1199440 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.5242. Min Act: -0.1700
Data Index: 3760522 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4617. Min Act: -0.1700
Data Index: 7364069 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4617. Min Act: -0.1700
Data Index: 6992856 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4617. Min Act: -0.1700
Data Index: 2006269 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.4617. Min Act: -0.1700
Data Index: 3505817 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1492. Min Range: -6.1492
Max Act: 5.3992. Min Act: -0.1700
Data Index: 5686575 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19