Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5515 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.5905. Min Act: -0.1700
Data Index: 1091662 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.5593. Min Act: -0.1700
Data Index: 51387 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3718. Min Act: -0.1700
Data Index: 7781800 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.3405. Min Act: -0.1700
Data Index: 1921769 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2780. Min Act: -0.1700
Data Index: 839898 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2780. Min Act: -0.1700
Data Index: 3475015 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2468. Min Act: -0.1700
Data Index: 8369024 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.2468. Min Act: -0.1700
Data Index: 8667968 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.1843. Min Act: -0.1700
Data Index: 7473347 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.1218. Min Act: -0.1700
Data Index: 5436917 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.1218. Min Act: -0.1700
Data Index: 6806630 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0905. Min Act: -0.1700
Data Index: 5051143 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0593. Min Act: -0.1700
Data Index: 4758576 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7156014 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7677140 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0593. Min Act: -0.1700
Data Index: 6641897 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0593. Min Act: -0.1700
Data Index: 6398496 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0280. Min Act: -0.1700
Data Index: 2256499 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6085488 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5905. Min Range: -5.5905
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6231814 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19