Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2986 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 905258 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0286. Min Act: -0.0003

Data Index: 435336 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1184923 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0263. Min Act: -0.0003

Data Index: 19133 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1034172 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0250. Min Act: -0.0003

Data Index: 153567 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1047232 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0223. Min Act: -0.0002

Data Index: 326350 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0217. Min Act: -0.0003

Data Index: 320578 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0196. Min Act: -0.0003

Data Index: 286478 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0210. Min Act: -0.0003

Data Index: 767665 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0201. Min Act: -0.0003

Data Index: 4008 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0204. Min Act: -0.0003

Data Index: 603792 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1315979 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0197. Min Act: -0.0003

Data Index: 836557 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0183. Min Act: -0.0003

Data Index: 362887 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1647830 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0182. Min Act: -0.0003

Data Index: 61326 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0181. Min Act: -0.0003

Data Index: 266157 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0181. Min Act: -0.0003

Data Index: 317024 (C4 (Web Text))

Max Activating Token Index: 252