Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.6042. Min Act: -0.1700
Data Index: 1357699 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.6042. Min Act: -0.1700
Data Index: 268730 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.5417. Min Act: -0.1700
Data Index: 8165753 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.4792. Min Act: -0.1700
Data Index: 3613576 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.5417. Min Act: -0.1700
Data Index: 920675 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.3542. Min Act: -0.1700
Data Index: 1296541 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.3542. Min Act: -0.1700
Data Index: 1731325 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.2917. Min Act: -0.1700
Data Index: 2658343 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.2917. Min Act: -0.1700
Data Index: 4093349 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.2917. Min Act: -0.1700
Data Index: 6754899 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1667. Min Act: -0.1700
Data Index: 2129856 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.2292. Min Act: -0.1700
Data Index: 3511976 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.2292. Min Act: -0.1700
Data Index: 8665827 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 5634963 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 4066578 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 2673772 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 958018 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 4112945 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 4641117 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6042. Min Range: -9.6042
Max Act: 9.1042. Min Act: -0.1700
Data Index: 5722086 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19