Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 806 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1582. Min Act: -0.0001

Data Index: 598813 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1435541 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1309. Min Act: -0.0000

Data Index: 436619 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1531156 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1571293 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1025549 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1367. Min Act: -0.0000

Data Index: 818001 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1613430 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1603061 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1402. Min Act: -0.0001

Data Index: 473339 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1490284 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1305. Min Act: -0.0000

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1176. Min Act: -0.0000

Data Index: 119966 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1256. Min Act: -0.0001

Data Index: 998099 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1381788 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1271. Min Act: -0.0000

Data Index: 987019 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1581217 (Python Code)

Max Activating Token Index: 944

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1377377 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1221. Min Act: -0.0001

Data Index: 936866 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1371180 (Python Code)

Max Activating Token Index: 1004