Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2078 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.4959. Min Act: -0.1700
Data Index: 871729 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3709. Min Act: -0.1700
Data Index: 1546659 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3709. Min Act: -0.1700
Data Index: 938191 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3709. Min Act: -0.1700
Data Index: 5249953 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3709. Min Act: -0.1700
Data Index: 7426733 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3397. Min Act: -0.1700
Data Index: 5435996 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3397. Min Act: -0.1700
Data Index: 2096163 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3084. Min Act: -0.1700
Data Index: 1421830 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3084. Min Act: -0.1700
Data Index: 6953831 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3084. Min Act: -0.1700
Data Index: 2325309 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.3084. Min Act: -0.1700
Data Index: 8319704 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2772. Min Act: -0.1700
Data Index: 3118365 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2772. Min Act: -0.1700
Data Index: 5696191 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2459. Min Act: -0.1700
Data Index: 5768783 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2459. Min Act: -0.1700
Data Index: 1905219 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2772. Min Act: -0.1700
Data Index: 3434186 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2459. Min Act: -0.1700
Data Index: 2872830 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2459. Min Act: -0.1700
Data Index: 5611714 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2772. Min Act: -0.1700
Data Index: 1969594 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4959. Min Range: -4.4959
Max Act: 4.2459. Min Act: -0.1700
Data Index: 4108013 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19