Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5057 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.9822. Min Act: -0.1700
Data Index: 8573858 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.9197. Min Act: -0.1700
Data Index: 6460357 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.9197. Min Act: -0.1700
Data Index: 8382193 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.7947. Min Act: -0.1700
Data Index: 2037551 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.7635. Min Act: -0.1700
Data Index: 3611690 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.7010. Min Act: -0.1700
Data Index: 6185876 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.6697. Min Act: -0.1700
Data Index: 3882673 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.6385. Min Act: -0.1700
Data Index: 6460358 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.6385. Min Act: -0.1700
Data Index: 53371 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5760. Min Act: -0.1700
Data Index: 4530103 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.6072. Min Act: -0.1700
Data Index: 7180594 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.6072. Min Act: -0.1700
Data Index: 7798551 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5760. Min Act: -0.1700
Data Index: 2997462 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5447. Min Act: -0.1700
Data Index: 6437403 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1632646 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5447. Min Act: -0.1700
Data Index: 3018423 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5135. Min Act: -0.1700
Data Index: 8127227 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1199556 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5135. Min Act: -0.1700
Data Index: 2691323 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9822. Min Range: -4.9822
Max Act: 4.5135. Min Act: -0.1700
Data Index: 72710 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19