Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5685. Min Range: -7.5685
Max Act: 7.5685. Min Act: -0.1700
Data Index: 3741123 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5685. Min Range: -7.5685
Max Act: 7.1935. Min Act: -0.1700
Data Index: 7035381 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5685. Min Range: -7.5685
Max Act: 7.1310. Min Act: -0.1700
Data Index: 8149100 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5685. Min Range: -7.5685
Max Act: 7.0372. Min Act: -0.1700
Data Index: 3607657 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.9747. Min Act: -0.1700
Data Index: 648131 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.9747. Min Act: -0.1700
Data Index: 5103439 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7872. Min Act: -0.1700
Data Index: 4366406 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7560. Min Act: -0.1700
Data Index: 7113481 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7560. Min Act: -0.1700
Data Index: 7141385 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7560. Min Act: -0.1700
Data Index: 8693819 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7247. Min Act: -0.1700
Data Index: 1018760 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.7247. Min Act: -0.1700
Data Index: 5539914 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6622. Min Act: -0.1700
Data Index: 2862442 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6622. Min Act: -0.1700
Data Index: 5103464 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6935. Min Act: -0.1700
Data Index: 2387671 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6622. Min Act: -0.1700
Data Index: 8151103 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6310. Min Act: -0.1700
Data Index: 7399234 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.5997. Min Act: -0.1700
Data Index: 1375545 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.5997. Min Act: -0.1700
Data Index: 4931042 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5685. Min Range: -7.5685
Max Act: 6.6310. Min Act: -0.1700
Data Index: 1584704 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19