Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1986 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.6473. Min Act: -0.1700
Data Index: 1652529 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.4285. Min Act: -0.1700
Data Index: 4140249 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.4285. Min Act: -0.1700
Data Index: 2336094 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3973. Min Act: -0.1700
Data Index: 3810299 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3973. Min Act: -0.1700
Data Index: 1640820 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3660. Min Act: -0.1700
Data Index: 7555782 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3348. Min Act: -0.1700
Data Index: 2659899 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3348. Min Act: -0.1700
Data Index: 1384995 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3035. Min Act: -0.1700
Data Index: 7287232 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3348. Min Act: -0.1700
Data Index: 2650947 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3035. Min Act: -0.1700
Data Index: 2397558 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.3035. Min Act: -0.1700
Data Index: 5557162 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2723. Min Act: -0.1700
Data Index: 5214950 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2723. Min Act: -0.1700
Data Index: 6213159 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2723. Min Act: -0.1700
Data Index: 7973409 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2410. Min Act: -0.1700
Data Index: 3685865 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2410. Min Act: -0.1700
Data Index: 7389998 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2410. Min Act: -0.1700
Data Index: 3153677 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2410. Min Act: -0.1700
Data Index: 4460893 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6473. Min Range: -6.6473
Max Act: 6.2098. Min Act: -0.1700
Data Index: 1004863 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19