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

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

Neuron 3295 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9630. Min Act: -0.0000

Data Index: 990403 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8205. Min Act: 0.0000

Data Index: 1087649 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1249992 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7725. Min Act: -0.0000

Data Index: 102026 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6824. Min Act: -0.0000

Data Index: 727953 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7014. Min Act: -0.0000

Data Index: 47736 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1080564 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6663. Min Act: -0.0000

Data Index: 888070 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6480. Min Act: -0.0000

Data Index: 700490 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6190. Min Act: 0.0001

Data Index: 978471 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1245345 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6500. Min Act: -0.0000

Data Index: 183071 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6280. Min Act: -0.0000

Data Index: 340327 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6234. Min Act: 0.0000

Data Index: 223511 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6141. Min Act: 0.0001

Data Index: 1293006 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6068. Min Act: -0.0000

Data Index: 781662 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6126. Min Act: -0.0000

Data Index: 340998 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6128. Min Act: -0.0000

Data Index: 38974 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5905. Min Act: 0.0001

Data Index: 1082865 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6054. Min Act: -0.0000

Data Index: 531553 (C4 (Web Text))

Max Activating Token Index: 378