Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.8914. Min Act: -0.1700
Data Index: 2775114 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.8914. Min Act: -0.1700
Data Index: 48702 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.8602. Min Act: -0.1700
Data Index: 4831782 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.8289. Min Act: -0.1700
Data Index: 2762050 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.7352. Min Act: -0.1700
Data Index: 1740439 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.7039. Min Act: -0.1700
Data Index: 4827301 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6727. Min Act: -0.1700
Data Index: 1330140 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5789. Min Act: -0.1700
Data Index: 3118215 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.6102. Min Act: -0.1700
Data Index: 5005992 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5789. Min Act: -0.1700
Data Index: 5463422 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5477. Min Act: -0.1700
Data Index: 6715771 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5477. Min Act: -0.1700
Data Index: 640543 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5477. Min Act: -0.1700
Data Index: 372481 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5477. Min Act: -0.1700
Data Index: 8538514 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 1725868 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.4852. Min Act: -0.1700
Data Index: 3534907 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.5164. Min Act: -0.1700
Data Index: 8482018 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.4539. Min Act: -0.1700
Data Index: 7620388 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.4227. Min Act: -0.1700
Data Index: 4701184 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8914. Min Range: -6.8914
Max Act: 6.4227. Min Act: -0.1700
Data Index: 7974649 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19