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

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

Neuron 3151 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.3274. Min Act: -0.0003

Data Index: 1412167 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.2652. Min Act: -0.0003

Data Index: 1517002 (Python Code)

Max Activating Token Index: 411

Text #2

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.2324. Min Act: -0.0003

Data Index: 1507497 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.2422. Min Act: -0.0003

Data Index: 1533546 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.2051. Min Act: -0.0003

Data Index: 1433795 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1980. Min Act: -0.0003

Data Index: 1475114 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1782. Min Act: -0.0003

Data Index: 1500941 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1416. Min Act: -0.0003

Data Index: 1582684 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1328. Min Act: -0.0003

Data Index: 1622489 (Python Code)

Max Activating Token Index: 39

Text #9

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1353. Min Act: -0.0003

Data Index: 1479339 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1336. Min Act: -0.0003

Data Index: 1460219 (Python Code)

Max Activating Token Index: 439

Text #11

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1304. Min Act: -0.0003

Data Index: 1513923 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1138. Min Act: -0.0003

Data Index: 1552081 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1138. Min Act: -0.0003

Data Index: 1613537 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1420. Min Act: -0.0003

Data Index: 1409643 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1063. Min Act: -0.0003

Data Index: 1366883 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0865. Min Act: -0.0003

Data Index: 1581445 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0772. Min Act: -0.0003

Data Index: 1590726 (Python Code)

Max Activating Token Index: 828

Text #18

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9629. Min Act: -0.0003

Data Index: 1516587 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9571. Min Act: -0.0003

Data Index: 1406010 (Python Code)

Max Activating Token Index: 10