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

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

Neuron 2562 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: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1592131 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0270. Min Act: -0.0003

Data Index: 73351 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0279. Min Act: -0.0003

Data Index: 629609 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0261. Min Act: -0.0003

Data Index: 887773 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1619487 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1561190 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1640539 (Python Code)

Max Activating Token Index: 770

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0257. Min Act: -0.0003

Data Index: 136878 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1443981 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1263267 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1077187 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0220. Min Act: -0.0003

Data Index: 199068 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0219. Min Act: -0.0003

Data Index: 858330 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1374016 (Python Code)

Max Activating Token Index: 820

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1073090 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1021172 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0236. Min Act: -0.0002

Data Index: 458662 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1564939 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1011538 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0230. Min Act: -0.0003

Data Index: 566706 (C4 (Web Text))

Max Activating Token Index: 560