Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1780 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0005

Data Index: 1070680 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1176740 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0205. Min Act: -0.0005

Data Index: 772024 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0204. Min Act: -0.0005

Data Index: 436107 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1449245 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0189. Min Act: -0.0005

Data Index: 756626 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0189. Min Act: -0.0005

Data Index: 625566 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1437951 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0189. Min Act: -0.0005

Data Index: 343411 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1278379 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0191. Min Act: -0.0005

Data Index: 251417 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0190. Min Act: -0.0005

Data Index: 339993 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0184. Min Act: -0.0005

Data Index: 257298 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0185. Min Act: -0.0005

Data Index: 1433911 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1352251 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0188. Min Act: -0.0005

Data Index: 429912 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0005

Data Index: 548645 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1270605 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1194541 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1118016 (C4 (Web Text))

Max Activating Token Index: 670