Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1821 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.7212. Min Act: -0.1700
Data Index: 8062329 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5337. Min Act: -0.1700
Data Index: 7706215 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.5024. Min Act: -0.1700
Data Index: 1880379 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4712. Min Act: -0.1700
Data Index: 873698 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1156744 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.3774. Min Act: -0.1700
Data Index: 5240805 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2837. Min Act: -0.1700
Data Index: 5812061 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2837. Min Act: -0.1700
Data Index: 5936395 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 3818573 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 8145775 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 6235456 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 5767640 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 5709660 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2837. Min Act: -0.1700
Data Index: 3782660 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 1945909 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 7358448 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6650080 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 2648416 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2524. Min Act: -0.1700
Data Index: 6298593 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7212. Min Range: -5.7212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6203067 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19