Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 561 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 632169 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1448077 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1053545 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1560276 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0246. Min Act: -0.0003

Data Index: 197342 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1208059 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1134601 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0256. Min Act: -0.0003

Data Index: 889411 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0002

Data Index: 548102 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0246. Min Act: -0.0003

Data Index: 879464 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0240. Min Act: -0.0002

Data Index: 595882 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0002

Data Index: 322456 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1440970 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0003

Data Index: 251697 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1450954 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1612359 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0003

Data Index: 506225 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1102261 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1526225 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0224. Min Act: -0.0003

Data Index: 920257 (C4 (Web Text))

Max Activating Token Index: 838