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

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

Neuron 74 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1007469 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6395. Min Act: -0.0000

Data Index: 22141 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.7209. Min Act: -0.0000

Data Index: 79265 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1081267 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6034. Min Act: -0.0000

Data Index: 570829 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6037. Min Act: -0.0000

Data Index: 860431 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6049. Min Act: -0.0000

Data Index: 770812 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1293812 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.6302. Min Act: -0.0000

Data Index: 15853 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5400. Min Act: -0.0000

Data Index: 870576 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5240. Min Act: -0.0000

Data Index: 652572 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5183. Min Act: -0.0000

Data Index: 220917 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.4720. Min Act: -0.0000

Data Index: 638491 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.4993. Min Act: -0.0000

Data Index: 623321 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5013. Min Act: -0.0000

Data Index: 869631 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.5865. Min Act: -0.0000

Data Index: 874506 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.4931. Min Act: -0.0000

Data Index: 934147 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.4765. Min Act: -0.0000

Data Index: 584917 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.7209. Min Range: -1.7209

Max Act: 1.4804. Min Act: -0.0000

Data Index: 1310760 (C4 (Web Text))

Max Activating Token Index: 889