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

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

Neuron 4720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0002

Data Index: 628352 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0364. Min Act: -0.0002

Data Index: 160665 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0327. Min Act: -0.0002

Data Index: 193792 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1135240 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0316. Min Act: -0.0002

Data Index: 980355 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0298. Min Act: -0.0002

Data Index: 249717 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0289. Min Act: -0.0002

Data Index: 329909 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1097970 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1143549 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0303. Min Act: -0.0002

Data Index: 940174 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0269. Min Act: -0.0002

Data Index: 609996 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1023585 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0279. Min Act: -0.0002

Data Index: 623097 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0292. Min Act: -0.0002

Data Index: 473939 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0291. Min Act: -0.0002

Data Index: 236526 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0264. Min Act: -0.0002

Data Index: 412381 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0290. Min Act: -0.0002

Data Index: 388314 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0283. Min Act: -0.0002

Data Index: 507876 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0275. Min Act: -0.0002

Data Index: 850401 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0272. Min Act: -0.0002

Data Index: 374056 (C4 (Web Text))

Max Activating Token Index: 41