Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 727 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.7331. Min Act: -0.1700
Data Index: 6849003 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.7331. Min Act: -0.1700
Data Index: 3463501 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.7171. Min Act: -0.1700
Data Index: 7204863 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.6851. Min Act: -0.1700
Data Index: 8209209 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.6691. Min Act: -0.1700
Data Index: 4553408 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5726. Min Act: -0.1700
Data Index: 8389358 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5726. Min Act: -0.1700
Data Index: 4996040 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5403. Min Act: -0.1700
Data Index: 4321562 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5403. Min Act: -0.1700
Data Index: 6176594 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5403. Min Act: -0.1700
Data Index: 8112931 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5726. Min Act: -0.1700
Data Index: 5094312 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5080. Min Act: -0.1700
Data Index: 8555611 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4756. Min Act: -0.1700
Data Index: 6066886 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5080. Min Act: -0.1700
Data Index: 5484388 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4918. Min Act: -0.1700
Data Index: 7116761 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4756. Min Act: -0.1700
Data Index: 4125392 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.5080. Min Act: -0.1700
Data Index: 2857890 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4756. Min Act: -0.1700
Data Index: 5638749 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4593. Min Act: -0.1700
Data Index: 7116759 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7331. Min Range: -2.7331
Max Act: 2.4593. Min Act: -0.1700
Data Index: 1307220 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19