Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2443 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0001

Data Index: 956032 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1191. Min Act: -0.0001

Data Index: 731099 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1235. Min Act: -0.0001

Data Index: 690710 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1106418 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1205. Min Act: -0.0001

Data Index: 915263 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1245. Min Act: -0.0001

Data Index: 197045 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1088. Min Act: -0.0001

Data Index: 652903 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1163. Min Act: -0.0001

Data Index: 846185 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1065566 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1047. Min Act: -0.0001

Data Index: 890834 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1084. Min Act: -0.0001

Data Index: 398002 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1270678 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1021. Min Act: -0.0001

Data Index: 584151 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1044. Min Act: -0.0001

Data Index: 2791 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1031. Min Act: -0.0001

Data Index: 264358 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1004. Min Act: -0.0001

Data Index: 544386 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1136247 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0990. Min Act: -0.0001

Data Index: 603788 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1021. Min Act: -0.0001

Data Index: 111937 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1061. Min Act: -0.0001

Data Index: 217279 (C4 (Web Text))

Max Activating Token Index: 938