Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3917 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: 0.0000

Data Index: 1590707 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1358. Min Act: -0.0001

Data Index: 311290 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1311. Min Act: -0.0001

Data Index: 755221 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1243. Min Act: -0.0001

Data Index: 661577 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1468505 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1265868 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1421807 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1417855 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1181. Min Act: -0.0001

Data Index: 734350 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1607735 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1140. Min Act: -0.0001

Data Index: 196067 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1639222 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1336197 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1585793 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1122. Min Act: 0.0000

Data Index: 1585665 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1178. Min Act: 0.0000

Data Index: 1485929 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1411367 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1650927 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1518327 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1603217 (Python Code)

Max Activating Token Index: 51