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

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

Neuron 1805 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: 0.0604. Min Range: -0.0604

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1629523 (Python Code)

Max Activating Token Index: 547

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1427196 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1376394 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1573273 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1472421 (Python Code)

Max Activating Token Index: 1022

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1460879 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1597466 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0507. Min Act: -0.0002

Data Index: 382331 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1495075 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1567876 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1385864 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1074714 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1195228 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1479659 (Python Code)

Max Activating Token Index: 726

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1434790 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0501. Min Act: -0.0002

Data Index: 301701 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1028253 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1541352 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1567916 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1442372 (Python Code)

Max Activating Token Index: 964