Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2033 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1765. Min Act: -0.0003

Data Index: 1392930 (Python Code)

Max Activating Token Index: 672

Text #1

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1707. Min Act: -0.0003

Data Index: 1381007 (Python Code)

Max Activating Token Index: 628

Text #2

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1639690 (Python Code)

Max Activating Token Index: 410

Text #3

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1387. Min Act: -0.0003

Data Index: 1622595 (Python Code)

Max Activating Token Index: 473

Text #4

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1384. Min Act: -0.0003

Data Index: 1499300 (Python Code)

Max Activating Token Index: 854

Text #5

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1312. Min Act: -0.0003

Data Index: 1432880 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1304. Min Act: -0.0003

Data Index: 1592135 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1380. Min Act: -0.0003

Data Index: 1608342 (Python Code)

Max Activating Token Index: 918

Text #8

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1424080 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1405511 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1191. Min Act: -0.0003

Data Index: 1611589 (Python Code)

Max Activating Token Index: 598

Text #11

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1333. Min Act: -0.0003

Data Index: 1638485 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1219. Min Act: -0.0003

Data Index: 1564575 (Python Code)

Max Activating Token Index: 949

Text #13

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1459644 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1210. Min Act: -0.0003

Data Index: 1591157 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1190. Min Act: -0.0003

Data Index: 1544533 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1627772 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1205. Min Act: -0.0003

Data Index: 1560936 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1590547 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1230. Min Act: -0.0003

Data Index: 1623930 (Python Code)

Max Activating Token Index: 649