Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2649991 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4664. Min Act: -0.1700
Data Index: 6538121 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5102466 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.3727. Min Act: -0.1700
Data Index: 92315 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 7977098 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2789. Min Act: -0.1700
Data Index: 6554945 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 8109275 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2164. Min Act: -0.1700
Data Index: 6109944 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 4091733 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 8392717 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 234601 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 4865597 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 758977 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 5052315 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2476. Min Act: -0.1700
Data Index: 1961712 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2164. Min Act: -0.1700
Data Index: 3418193 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2225747 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.2164. Min Act: -0.1700
Data Index: 4097172 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1851. Min Act: -0.1700
Data Index: 5660735 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2092169 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19