Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 49 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5878. Min Act: -0.0000

Data Index: 570086 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1103049 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5872. Min Act: -0.0000

Data Index: 82841 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5425. Min Act: -0.0000

Data Index: 97488 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4708. Min Act: -0.0000

Data Index: 108728 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5687. Min Act: -0.0000

Data Index: 867429 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1240780 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1112889 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5206. Min Act: -0.0000

Data Index: 465035 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5124. Min Act: -0.0000

Data Index: 62939 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1055485 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4580. Min Act: 0.0000

Data Index: 16919 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4754. Min Act: -0.0000

Data Index: 861532 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1130590 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.5071. Min Act: -0.0000

Data Index: 98936 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1050122 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1279584 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4516. Min Act: -0.0000

Data Index: 702344 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1072046 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.5878. Min Range: -0.5878

Max Act: 0.4473. Min Act: -0.0000

Data Index: 201236 (C4 (Web Text))

Max Activating Token Index: 807