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

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

Neuron 5100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0000

Data Index: 527865 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1267435 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1023797 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1036273 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1410. Min Act: -0.0000

Data Index: 136314 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1360. Min Act: -0.0000

Data Index: 694702 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1355. Min Act: -0.0000

Data Index: 852494 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1321. Min Act: -0.0000

Data Index: 830613 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1359. Min Act: -0.0000

Data Index: 682758 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1178947 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1317. Min Act: -0.0000

Data Index: 318293 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1351. Min Act: -0.0000

Data Index: 218636 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1337. Min Act: -0.0000

Data Index: 345039 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1273. Min Act: -0.0000

Data Index: 965604 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1248. Min Act: -0.0000

Data Index: 800978 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1236. Min Act: -0.0000

Data Index: 510202 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1185. Min Act: -0.0000

Data Index: 994855 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1270. Min Act: -0.0000

Data Index: 115195 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1181. Min Act: -0.0000

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1206. Min Act: -0.0000

Data Index: 621294 (C4 (Web Text))

Max Activating Token Index: 868