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

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

Neuron 4895 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: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: -0.0002

Data Index: 1384058 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1468. Min Act: -0.0002

Data Index: 1424161 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1399183 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1619533 (Python Code)

Max Activating Token Index: 598

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1404816 (Python Code)

Max Activating Token Index: 388

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1492284 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1410. Min Act: -0.0002

Data Index: 1598255 (Python Code)

Max Activating Token Index: 704

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1285. Min Act: -0.0002

Data Index: 1417154 (Python Code)

Max Activating Token Index: 593

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1581988 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1574573 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1525786 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1522940 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1621444 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1407682 (Python Code)

Max Activating Token Index: 347

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1494219 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1590761 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1431429 (Python Code)

Max Activating Token Index: 653

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1401753 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1480317 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1642066 (Python Code)

Max Activating Token Index: 294