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

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

Neuron 3594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1700. Min Act: -0.0000

Data Index: 435885 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1468910 (Python Code)

Max Activating Token Index: 951

Text #2

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1573387 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1218765 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1607041 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1369498 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1395166 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1566468 (Python Code)

Max Activating Token Index: 292

Text #8

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1317. Min Act: -0.0000

Data Index: 192855 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1479721 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1154861 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1383548 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1601590 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1562819 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1598440 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1616239 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1190. Min Act: -0.0000

Data Index: 666386 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1411687 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1118492 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1407214 (Python Code)

Max Activating Token Index: 116