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

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

Neuron 748 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0244. Min Act: -0.0004

Data Index: 334216 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0225. Min Act: -0.0004

Data Index: 805986 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0004

Data Index: 223668 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1071108 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0205. Min Act: -0.0004

Data Index: 791117 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0215. Min Act: -0.0004

Data Index: 480655 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0192. Min Act: -0.0004

Data Index: 545061 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0204. Min Act: -0.0004

Data Index: 1463050 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0203. Min Act: -0.0004

Data Index: 952241 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0205. Min Act: -0.0004

Data Index: 737598 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0200. Min Act: -0.0004

Data Index: 901683 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0186. Min Act: -0.0004

Data Index: 587957 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0181. Min Act: -0.0004

Data Index: 1017398 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0195. Min Act: -0.0004

Data Index: 343547 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1067708 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1419843 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0181. Min Act: -0.0004

Data Index: 1076889 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0168. Min Act: -0.0004

Data Index: 1438658 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0183. Min Act: -0.0004

Data Index: 212096 (C4 (Web Text))

Max Activating Token Index: 248