Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.8785. Min Act: -0.1700
Data Index: 911300 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.8160. Min Act: -0.1700
Data Index: 5710820 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.8160. Min Act: -0.1700
Data Index: 1070392 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.7535. Min Act: -0.1700
Data Index: 324278 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.6910. Min Act: -0.1700
Data Index: 4041281 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5660. Min Act: -0.1700
Data Index: 6660844 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5660. Min Act: -0.1700
Data Index: 7885132 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5035. Min Act: -0.1700
Data Index: 4824795 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5035. Min Act: -0.1700
Data Index: 5710822 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5035. Min Act: -0.1700
Data Index: 481604 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.5035. Min Act: -0.1700
Data Index: 4546577 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.4410. Min Act: -0.1700
Data Index: 8568238 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3785. Min Act: -0.1700
Data Index: 1916317 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3785. Min Act: -0.1700
Data Index: 4081388 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.4410. Min Act: -0.1700
Data Index: 2925596 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3160. Min Act: -0.1700
Data Index: 1323510 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3160. Min Act: -0.1700
Data Index: 5710817 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3160. Min Act: -0.1700
Data Index: 5710819 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3160. Min Act: -0.1700
Data Index: 8239599 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8785. Min Range: -8.8785
Max Act: 8.3160. Min Act: -0.1700
Data Index: 4696776 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19