Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2049 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.5563. Min Act: -0.1700
Data Index: 858485 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.5563. Min Act: -0.1700
Data Index: 7322814 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.4938. Min Act: -0.1700
Data Index: 247862 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.4938. Min Act: -0.1700
Data Index: 3571560 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.4313. Min Act: -0.1700
Data Index: 6935099 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.3063. Min Act: -0.1700
Data Index: 5796761 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.2438. Min Act: -0.1700
Data Index: 5991995 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.3063. Min Act: -0.1700
Data Index: 7180618 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.2438. Min Act: -0.1700
Data Index: 4350278 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.2438. Min Act: -0.1700
Data Index: 5620545 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.3063. Min Act: -0.1700
Data Index: 2448381 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 5343014 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1813. Min Act: -0.1700
Data Index: 3195862 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1813. Min Act: -0.1700
Data Index: 3408356 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 6506561 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 3238559 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 7586731 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 331628 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 7233334 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5563. Min Range: -10.5563
Max Act: 10.1188. Min Act: -0.1700
Data Index: 8685775 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19