Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.5984. Min Act: -0.1700
Data Index: 3521019 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2314003 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.3796. Min Act: -0.1700
Data Index: 7730833 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.3484. Min Act: -0.1700
Data Index: 4988348 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.2546. Min Act: -0.1700
Data Index: 3534599 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.1609. Min Act: -0.1700
Data Index: 5757684 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.1609. Min Act: -0.1700
Data Index: 1019412 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.1609. Min Act: -0.1700
Data Index: 6850928 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.1296. Min Act: -0.1700
Data Index: 1649901 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0984. Min Act: -0.1700
Data Index: 8620617 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0671. Min Act: -0.1700
Data Index: 6019294 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0671. Min Act: -0.1700
Data Index: 5217171 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0671. Min Act: -0.1700
Data Index: 2869398 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0359. Min Act: -0.1700
Data Index: 6337537 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5984. Min Range: -6.5984
Max Act: 5.9734. Min Act: -0.1700
Data Index: 6390120 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5984. Min Range: -6.5984
Max Act: 6.0046. Min Act: -0.1700
Data Index: 2722389 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5984. Min Range: -6.5984
Max Act: 5.9421. Min Act: -0.1700
Data Index: 808242 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5984. Min Range: -6.5984
Max Act: 5.9421. Min Act: -0.1700
Data Index: 2852073 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5984. Min Range: -6.5984
Max Act: 5.9421. Min Act: -0.1700
Data Index: 3495720 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5984. Min Range: -6.5984
Max Act: 5.9421. Min Act: -0.1700
Data Index: 8616059 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19