Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2018638 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.4986. Min Act: -0.1700
Data Index: 5001598 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.4674. Min Act: -0.1700
Data Index: 6470891 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.3736. Min Act: -0.1700
Data Index: 7495545 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.3111. Min Act: -0.1700
Data Index: 6981580 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.3111. Min Act: -0.1700
Data Index: 4815949 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.2486. Min Act: -0.1700
Data Index: 7443950 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.2486. Min Act: -0.1700
Data Index: 7293856 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.1861. Min Act: -0.1700
Data Index: 5583222 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.1861. Min Act: -0.1700
Data Index: 2271184 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0924. Min Act: -0.1700
Data Index: 6798079 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0611. Min Act: -0.1700
Data Index: 5109626 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 7669799 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 534981 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 5278822 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 1501320 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 190057 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8111. Min Range: -6.8111
Max Act: 6.0299. Min Act: -0.1700
Data Index: 336463 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8111. Min Range: -6.8111
Max Act: 5.9986. Min Act: -0.1700
Data Index: 8342028 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8111. Min Range: -6.8111
Max Act: 5.9986. Min Act: -0.1700
Data Index: 8357516 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19