Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2750188 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.1384. Min Act: -0.1700
Data Index: 6636997 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.1072. Min Act: -0.1700
Data Index: 512906 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.1072. Min Act: -0.1700
Data Index: 2236178 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0759. Min Act: -0.1700
Data Index: 6599317 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0134. Min Act: -0.1700
Data Index: 7198438 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0134. Min Act: -0.1700
Data Index: 5946314 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0134. Min Act: -0.1700
Data Index: 6599696 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0134. Min Act: -0.1700
Data Index: 5506348 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6521114 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2322. Min Range: -4.2322
Max Act: 4.0134. Min Act: -0.1700
Data Index: 602519 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9509. Min Act: -0.1700
Data Index: 7699659 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9196. Min Act: -0.1700
Data Index: 717454 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9509. Min Act: -0.1700
Data Index: 6021309 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9509. Min Act: -0.1700
Data Index: 2262575 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9509. Min Act: -0.1700
Data Index: 5589213 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9196. Min Act: -0.1700
Data Index: 6026142 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9196. Min Act: -0.1700
Data Index: 8624078 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.9196. Min Act: -0.1700
Data Index: 4042693 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2322. Min Range: -4.2322
Max Act: 3.8883. Min Act: -0.1700
Data Index: 4019226 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19