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

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

Neuron 2769 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1999. Min Act: -0.0002

Data Index: 260982 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1566. Min Act: -0.0002

Data Index: 807711 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1630. Min Act: -0.0002

Data Index: 316984 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1508. Min Act: -0.0002

Data Index: 984499 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1492. Min Act: -0.0002

Data Index: 1080550 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1158365 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1318. Min Act: -0.0002

Data Index: 319529 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1643337 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1018305 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1551852 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1588647 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1289. Min Act: -0.0002

Data Index: 650283 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1298141 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1180. Min Act: -0.0002

Data Index: 921815 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1231. Min Act: -0.0001

Data Index: 796650 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1305. Min Act: -0.0002

Data Index: 415578 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1441. Min Act: -0.0002

Data Index: 725695 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1292. Min Act: -0.0002

Data Index: 915382 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1286. Min Act: -0.0001

Data Index: 831864 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1343. Min Act: -0.0002

Data Index: 781035 (C4 (Web Text))

Max Activating Token Index: 769