Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1162332 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1608121 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0316. Min Act: -0.0001

Data Index: 874687 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1017421 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1016054 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0229. Min Act: -0.0001

Data Index: 261838 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0267. Min Act: -0.0001

Data Index: 972757 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1522292 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0264. Min Act: -0.0001

Data Index: 228041 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0263. Min Act: -0.0001

Data Index: 777137 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0243. Min Act: -0.0001

Data Index: 132039 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0271. Min Act: -0.0001

Data Index: 720757 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1343263 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0281. Min Act: -0.0001

Data Index: 889356 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0261. Min Act: -0.0001

Data Index: 145809 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0246. Min Act: -0.0001

Data Index: 635536 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1129753 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0260. Min Act: -0.0001

Data Index: 907766 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0278. Min Act: -0.0001

Data Index: 502268 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1339333 (C4 (Web Text))

Max Activating Token Index: 828