Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0405. Min Range: -8.0405
Max Act: 8.0405. Min Act: -0.1700
Data Index: 8092932 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.9780. Min Act: -0.1700
Data Index: 5412791 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 3092335 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 2804684 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 5406437 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 870533 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 7947195 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.8530. Min Act: -0.1700
Data Index: 4588824 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7905. Min Act: -0.1700
Data Index: 6681932 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7905. Min Act: -0.1700
Data Index: 4592566 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7905. Min Act: -0.1700
Data Index: 2056318 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 4148588 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 2513049 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 7996934 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 6115444 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 1897450 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.7280. Min Act: -0.1700
Data Index: 3160139 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.6655. Min Act: -0.1700
Data Index: 4906518 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.6655. Min Act: -0.1700
Data Index: 6094727 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0405. Min Range: -8.0405
Max Act: 7.6655. Min Act: -0.1700
Data Index: 3243085 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19