Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.8421. Min Act: -0.1700
Data Index: 6072676 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.7484. Min Act: -0.1700
Data Index: 5238059 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 7337005 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 1005310 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 1353119 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 2816510 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.5921. Min Act: -0.1700
Data Index: 681799 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.5921. Min Act: -0.1700
Data Index: 3346810 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.5921. Min Act: -0.1700
Data Index: 7689966 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.5609. Min Act: -0.1700
Data Index: 518038 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4984. Min Act: -0.1700
Data Index: 4596708 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4671. Min Act: -0.1700
Data Index: 4209995 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4359. Min Act: -0.1700
Data Index: 7410566 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3525109 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4046. Min Act: -0.1700
Data Index: 6233333 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.3734. Min Act: -0.1700
Data Index: 757126 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.4046. Min Act: -0.1700
Data Index: 641122 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.3421. Min Act: -0.1700
Data Index: 2455135 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.3109. Min Act: -0.1700
Data Index: 4158117 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8421. Min Range: -7.8421
Max Act: 7.3109. Min Act: -0.1700
Data Index: 2325972 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19