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

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

Neuron 4910 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1397622 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1626869 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1529972 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1363564 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1656512 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1538192 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1515513 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1498554 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1405636 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1395672 (Python Code)

Max Activating Token Index: 1006

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1250. Min Act: -0.0001

Data Index: 381833 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1066958 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1328. Min Act: -0.0000

Data Index: 973577 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1450. Min Act: -0.0000

Data Index: 76847 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1207. Min Act: -0.0000

Data Index: 447863 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1118473 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1626937 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1255. Min Act: -0.0001

Data Index: 996000 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1116. Min Act: -0.0000

Data Index: 605047 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1557573 (Python Code)

Max Activating Token Index: 923