Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.7349. Min Act: -0.1700
Data Index: 6157629 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.7349. Min Act: -0.1700
Data Index: 4704211 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.6099. Min Act: -0.1700
Data Index: 2179283 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.7349. Min Act: -0.1700
Data Index: 7166761 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.6099. Min Act: -0.1700
Data Index: 5055656 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.5474. Min Act: -0.1700
Data Index: 8500758 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.5474. Min Act: -0.1700
Data Index: 7250173 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4849. Min Act: -0.1700
Data Index: 2179284 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4849. Min Act: -0.1700
Data Index: 2986990 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.5474. Min Act: -0.1700
Data Index: 6157626 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4849. Min Act: -0.1700
Data Index: 7669965 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4224. Min Act: -0.1700
Data Index: 1578531 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4849. Min Act: -0.1700
Data Index: 6993537 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.4224. Min Act: -0.1700
Data Index: 1656568 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.3599. Min Act: -0.1700
Data Index: 4620189 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.2974. Min Act: -0.1700
Data Index: 2801317 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.2974. Min Act: -0.1700
Data Index: 4247084 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.3599. Min Act: -0.1700
Data Index: 6027988 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.2974. Min Act: -0.1700
Data Index: 2723714 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7349. Min Range: -8.7349
Max Act: 8.2974. Min Act: -0.1700
Data Index: 3046911 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19