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

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

Neuron 552 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: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0003

Data Index: 577728 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1020416 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1163018 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0231. Min Act: -0.0003

Data Index: 962305 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0003

Data Index: 379071 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1143874 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1014552 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0206. Min Act: -0.0003

Data Index: 86444 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0202. Min Act: -0.0003

Data Index: 668936 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0204. Min Act: -0.0003

Data Index: 483875 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0203. Min Act: -0.0003

Data Index: 581278 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0207. Min Act: -0.0003

Data Index: 785694 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0202. Min Act: -0.0004

Data Index: 570521 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0206. Min Act: -0.0003

Data Index: 490363 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0204. Min Act: -0.0003

Data Index: 42701 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0191. Min Act: -0.0003

Data Index: 912649 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0200. Min Act: -0.0003

Data Index: 252162 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0197. Min Act: -0.0003

Data Index: 713333 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0204. Min Act: -0.0003

Data Index: 330919 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0195. Min Act: -0.0003

Data Index: 296644 (C4 (Web Text))

Max Activating Token Index: 227