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

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

Neuron 1777 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0001

Data Index: 171879 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1062374 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1617. Min Act: -0.0001

Data Index: 406049 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1565. Min Act: -0.0001

Data Index: 919349 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1497. Min Act: -0.0001

Data Index: 84398 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1590. Min Act: -0.0001

Data Index: 893936 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1505. Min Act: -0.0001

Data Index: 236444 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1473. Min Act: -0.0001

Data Index: 179190 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1465. Min Act: -0.0001

Data Index: 227818 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1570. Min Act: -0.0001

Data Index: 452234 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1288517 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1552. Min Act: -0.0001

Data Index: 750370 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1365. Min Act: -0.0001

Data Index: 915325 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1352. Min Act: -0.0001

Data Index: 677348 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1381. Min Act: -0.0001

Data Index: 313259 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1460. Min Act: -0.0001

Data Index: 976808 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1350. Min Act: -0.0001

Data Index: 859791 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1347. Min Act: -0.0001

Data Index: 160060 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1263. Min Act: -0.0001

Data Index: 142325 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1224. Min Act: -0.0001

Data Index: 28790 (C4 (Web Text))

Max Activating Token Index: 400