Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1349 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1102997 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1613. Min Act: -0.0002

Data Index: 731849 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1640. Min Act: -0.0002

Data Index: 175460 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1640. Min Act: -0.0002

Data Index: 401310 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1636. Min Act: -0.0002

Data Index: 688135 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1520. Min Act: -0.0002

Data Index: 172953 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1497. Min Act: -0.0002

Data Index: 1168464 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1141349 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1417. Min Act: -0.0002

Data Index: 826880 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1420. Min Act: -0.0002

Data Index: 279570 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1397. Min Act: -0.0002

Data Index: 666600 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1475. Min Act: -0.0002

Data Index: 568927 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1433. Min Act: -0.0002

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1507. Min Act: -0.0002

Data Index: 40740 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1418. Min Act: -0.0002

Data Index: 1256774 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1417. Min Act: -0.0002

Data Index: 1033245 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1004661 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1361. Min Act: -0.0002

Data Index: 925653 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1448. Min Act: -0.0002

Data Index: 130444 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1377. Min Act: -0.0002

Data Index: 916712 (C4 (Web Text))

Max Activating Token Index: 74