Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1698 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0002

Data Index: 982602 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0581. Min Act: -0.0002

Data Index: 910288 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1598475 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0577. Min Act: -0.0003

Data Index: 694562 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1057718 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0584. Min Act: -0.0002

Data Index: 527606 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0576. Min Act: -0.0003

Data Index: 890558 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1496553 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1475696 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0575. Min Act: -0.0003

Data Index: 420143 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1429795 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0548. Min Act: -0.0004

Data Index: 541980 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0548. Min Act: -0.0003

Data Index: 85986 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1560970 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0535. Min Act: -0.0003

Data Index: 141154 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1614905 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1209388 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1391315 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0532. Min Act: -0.0003

Data Index: 690749 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1448659 (Python Code)

Max Activating Token Index: 455