Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1450 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0321. Min Act: -0.0004

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0262. Min Act: -0.0005

Data Index: 757459 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0256. Min Act: -0.0005

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0245. Min Act: -0.0004

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1117460 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0251. Min Act: -0.0005

Data Index: 687631 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0248. Min Act: -0.0005

Data Index: 223551 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0243. Min Act: -0.0005

Data Index: 365974 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0237. Min Act: -0.0005

Data Index: 438018 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0226. Min Act: -0.0004

Data Index: 175936 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0230. Min Act: -0.0004

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1215703 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1231991 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0224. Min Act: -0.0005

Data Index: 1188428 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0213. Min Act: -0.0005

Data Index: 1198248 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0215. Min Act: -0.0004

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0209. Min Act: -0.0005

Data Index: 1242845 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0210. Min Act: -0.0005

Data Index: 440262 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.0321. Min Range: -0.0321

Max Act: 0.0206. Min Act: -0.0004

Data Index: 417899 (C4 (Web Text))

Max Activating Token Index: 847