Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1081 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.1928. Min Act: -0.0002

Data Index: 90553 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.2130. Min Act: -0.0002

Data Index: 531098 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.1735. Min Act: -0.0002

Data Index: 405112 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.0562. Min Act: -0.0002

Data Index: 934302 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.1195. Min Act: -0.0002

Data Index: 1238379 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.0260. Min Act: -0.0003

Data Index: 881935 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9836. Min Act: -0.0002

Data Index: 181185 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 2.2130. Min Range: -2.2130

Max Act: 2.0236. Min Act: -0.0002

Data Index: 764433 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9936. Min Act: -0.0002

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9699. Min Act: -0.0002

Data Index: 751512 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9601. Min Act: -0.0002

Data Index: 793590 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9097. Min Act: -0.0003

Data Index: 1027165 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9464. Min Act: -0.0002

Data Index: 500934 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9037. Min Act: -0.0002

Data Index: 608897 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9095. Min Act: -0.0002

Data Index: 481066 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9412. Min Act: -0.0002

Data Index: 1179430 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.8994. Min Act: -0.0002

Data Index: 520341 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9254. Min Act: -0.0002

Data Index: 301988 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9071. Min Act: -0.0002

Data Index: 1187878 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 2.2130. Min Range: -2.2130

Max Act: 1.9229. Min Act: -0.0002

Data Index: 1007456 (C4 (Web Text))

Max Activating Token Index: 730