Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1255. Min Act: -0.0001

Data Index: 429347 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1268. Min Act: -0.0002

Data Index: 51526 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0002

Data Index: 588633 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1220. Min Act: -0.0003

Data Index: 651241 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1200. Min Act: 0.0000

Data Index: 1202186 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1137275 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1193. Min Act: -0.0002

Data Index: 575930 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1193. Min Act: -0.0003

Data Index: 94772 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1186. Min Act: -0.0004

Data Index: 61196 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1170. Min Act: -0.0003

Data Index: 1319460 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1171. Min Act: -0.0003

Data Index: 1330148 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1159. Min Act: -0.0004

Data Index: 518733 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1204627 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1143. Min Act: -0.0003

Data Index: 506420 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1118. Min Act: -0.0002

Data Index: 372004 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1117. Min Act: -0.0002

Data Index: 293370 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1137. Min Act: -0.0003

Data Index: 643971 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1122. Min Act: -0.0003

Data Index: 100133 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1131. Min Act: 0.0001

Data Index: 710035 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1166. Min Act: -0.0003

Data Index: 455026 (C4 (Web Text))

Max Activating Token Index: 373