Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.3451. Min Act: -0.1700
Data Index: 6779620 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.3451. Min Act: -0.1700
Data Index: 5251962 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.2513. Min Act: -0.1700
Data Index: 2956892 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.2201. Min Act: -0.1700
Data Index: 5981921 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1888. Min Act: -0.1700
Data Index: 5610969 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1888. Min Act: -0.1700
Data Index: 6400957 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1888. Min Act: -0.1700
Data Index: 8348767 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1888. Min Act: -0.1700
Data Index: 2088595 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1576. Min Act: -0.1700
Data Index: 3312254 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1576. Min Act: -0.1700
Data Index: 6356374 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1576. Min Act: -0.1700
Data Index: 5392941 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1576. Min Act: -0.1700
Data Index: 6869709 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.1263. Min Act: -0.1700
Data Index: 8256464 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0951. Min Act: -0.1700
Data Index: 126830 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0951. Min Act: -0.1700
Data Index: 689474 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0951. Min Act: -0.1700
Data Index: 975495 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0638. Min Act: -0.1700
Data Index: 6220093 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0638. Min Act: -0.1700
Data Index: 4876615 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0951. Min Act: -0.1700
Data Index: 2442412 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3451. Min Range: -7.3451
Max Act: 7.0638. Min Act: -0.1700
Data Index: 2139411 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19