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

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

Neuron 308 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: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0003

Data Index: 417444 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0300. Min Act: -0.0003

Data Index: 396591 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1202679 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0297. Min Act: -0.0003

Data Index: 310996 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0302. Min Act: -0.0003

Data Index: 529664 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0299. Min Act: -0.0003

Data Index: 257843 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1060989 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1122669 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0294. Min Act: -0.0003

Data Index: 781332 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0289. Min Act: -0.0003

Data Index: 739371 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0293. Min Act: -0.0004

Data Index: 421206 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0279. Min Act: -0.0003

Data Index: 26860 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0282. Min Act: -0.0003

Data Index: 733808 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0288. Min Act: -0.0004

Data Index: 234896 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0279. Min Act: -0.0004

Data Index: 7228 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0268. Min Act: -0.0003

Data Index: 724927 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1260737 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0282. Min Act: -0.0003

Data Index: 566512 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0277. Min Act: -0.0003

Data Index: 726175 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0274. Min Act: -0.0003

Data Index: 730400 (C4 (Web Text))

Max Activating Token Index: 141