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

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

Neuron 96 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: 0.0309. Min Range: -0.0309

Max Act: 0.0302. Min Act: -0.0002

Data Index: 118566 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 293635 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0290. Min Act: -0.0002

Data Index: 813768 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1082724 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0002

Data Index: 546198 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0002

Data Index: 201346 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0002

Data Index: 576112 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0002

Data Index: 852377 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0244. Min Act: -0.0003

Data Index: 949201 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1138336 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1342357 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0236. Min Act: -0.0002

Data Index: 554784 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0236. Min Act: -0.0002

Data Index: 693571 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0229. Min Act: -0.0003

Data Index: 637148 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1291946 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0003

Data Index: 519690 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0218. Min Act: -0.0003

Data Index: 122948 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0221. Min Act: -0.0003

Data Index: 905406 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0222. Min Act: -0.0003

Data Index: 732870 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0217. Min Act: -0.0002

Data Index: 218348 (C4 (Web Text))

Max Activating Token Index: 495