Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.7492. Min Act: -0.1700
Data Index: 7313168 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.6242. Min Act: -0.1700
Data Index: 7329273 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.5617. Min Act: -0.1700
Data Index: 2470376 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.5929. Min Act: -0.1700
Data Index: 4900054 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.4679. Min Act: -0.1700
Data Index: 3645872 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.3742. Min Act: -0.1700
Data Index: 2598472 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.4054. Min Act: -0.1700
Data Index: 2933467 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.3429. Min Act: -0.1700
Data Index: 15245 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2804. Min Act: -0.1700
Data Index: 7754028 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2492. Min Act: -0.1700
Data Index: 8704497 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2492. Min Act: -0.1700
Data Index: 7481717 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2179. Min Act: -0.1700
Data Index: 6035967 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2179. Min Act: -0.1700
Data Index: 7005184 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2179. Min Act: -0.1700
Data Index: 3834903 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2492. Min Act: -0.1700
Data Index: 2756997 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.1867. Min Act: -0.1700
Data Index: 8417671 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.1867. Min Act: -0.1700
Data Index: 8757533 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.2179. Min Act: -0.1700
Data Index: 7697573 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.1554. Min Act: -0.1700
Data Index: 838128 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7492. Min Range: -6.7492
Max Act: 6.1554. Min Act: -0.1700
Data Index: 315176 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19