Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 266 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1501225 (Python Code)

Max Activating Token Index: 550

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1621204 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1457. Min Act: 0.0002

Data Index: 1387639 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1647137 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1412843 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1457146 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1419444 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1632581 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1392280 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1247. Min Act: 0.0010

Data Index: 1538780 (Python Code)

Max Activating Token Index: 480

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1399309 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1290. Min Act: 0.0000

Data Index: 1577437 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1293. Min Act: 0.0008

Data Index: 1566497 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1300. Min Act: -0.0003

Data Index: 1372866 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1443397 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1423561 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1600343 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1620831 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1218. Min Act: 0.0016

Data Index: 1483238 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1219. Min Act: 0.0001

Data Index: 1368281 (Python Code)

Max Activating Token Index: 70