Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.5603. Min Act: -0.1700
Data Index: 1180061 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.5603. Min Act: -0.1700
Data Index: 5693808 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.4040. Min Act: -0.1700
Data Index: 1862977 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.3415. Min Act: -0.1700
Data Index: 4944170 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.3103. Min Act: -0.1700
Data Index: 3018940 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.3103. Min Act: -0.1700
Data Index: 737005 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2790. Min Act: -0.1700
Data Index: 7608946 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2478. Min Act: -0.1700
Data Index: 1740892 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2478. Min Act: -0.1700
Data Index: 7289501 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2165. Min Act: -0.1700
Data Index: 3282672 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2165. Min Act: -0.1700
Data Index: 2344680 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2165. Min Act: -0.1700
Data Index: 6812675 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2165. Min Act: -0.1700
Data Index: 4453913 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.2165. Min Act: -0.1700
Data Index: 1070797 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1853. Min Act: -0.1700
Data Index: 6300947 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1853. Min Act: -0.1700
Data Index: 7926334 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1540. Min Act: -0.1700
Data Index: 4274575 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1853. Min Act: -0.1700
Data Index: 704118 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1540. Min Act: -0.1700
Data Index: 3300723 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5603. Min Range: -6.5603
Max Act: 6.1540. Min Act: -0.1700
Data Index: 1895380 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19