Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.3959. Min Act: -0.1700
Data Index: 443122 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.3334. Min Act: -0.1700
Data Index: 4174007 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.1772. Min Act: -0.1700
Data Index: 486005 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.1459. Min Act: -0.1700
Data Index: 4238900 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.1147. Min Act: -0.1700
Data Index: 2166838 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.1147. Min Act: -0.1700
Data Index: 7167623 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.0834. Min Act: -0.1700
Data Index: 3248135 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.0834. Min Act: -0.1700
Data Index: 434564 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.9897. Min Act: -0.1700
Data Index: 8136142 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.9897. Min Act: -0.1700
Data Index: 486004 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3959. Min Range: -7.3959
Max Act: 7.0209. Min Act: -0.1700
Data Index: 486008 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.9897. Min Act: -0.1700
Data Index: 1281968 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.9584. Min Act: -0.1700
Data Index: 2166846 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.9272. Min Act: -0.1700
Data Index: 5280006 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3865546 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.8022. Min Act: -0.1700
Data Index: 4438723 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.7709. Min Act: -0.1700
Data Index: 2166847 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.7397. Min Act: -0.1700
Data Index: 5514673 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.7709. Min Act: -0.1700
Data Index: 2166848 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3959. Min Range: -7.3959
Max Act: 6.7397. Min Act: -0.1700
Data Index: 1281692 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19