Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0335. Min Act: -0.0001

Data Index: 656529 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1396034 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1379606 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0263. Min Act: -0.0001

Data Index: 13231 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0231. Min Act: -0.0001

Data Index: 719964 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0227. Min Act: -0.0001

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1252869 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1095923 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0210. Min Act: -0.0001

Data Index: 489712 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0257. Min Act: -0.0001

Data Index: 896156 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1159087 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0206. Min Act: -0.0001

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1045167 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0224. Min Act: -0.0001

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1587224 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1599909 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1136303 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0213. Min Act: -0.0001

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1436484 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1654796 (Python Code)

Max Activating Token Index: 668