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

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

Neuron 1227 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1971. Min Act: -0.0002

Data Index: 559869 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1627. Min Act: -0.0002

Data Index: 960858 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1187445 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1607. Min Act: -0.0002

Data Index: 674308 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1311056 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1548. Min Act: -0.0002

Data Index: 623199 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1522. Min Act: -0.0002

Data Index: 30604 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1474. Min Act: -0.0002

Data Index: 71230 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1476. Min Act: -0.0002

Data Index: 569694 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1085345 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1435. Min Act: -0.0002

Data Index: 190263 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1359. Min Act: -0.0002

Data Index: 597797 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1403. Min Act: -0.0002

Data Index: 360430 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1412. Min Act: -0.0002

Data Index: 337201 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1357. Min Act: -0.0002

Data Index: 485646 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1280. Min Act: -0.0002

Data Index: 399712 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1384. Min Act: -0.0002

Data Index: 703050 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1648. Min Act: -0.0002

Data Index: 1155036 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1330. Min Act: -0.0002

Data Index: 278970 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1090391 (C4 (Web Text))

Max Activating Token Index: 942