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

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

Neuron 1533 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 310850 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1042015 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1035669 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0641. Min Act: -0.0000

Data Index: 41667 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0636. Min Act: -0.0002

Data Index: 585541 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0627. Min Act: -0.0003

Data Index: 350190 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0614. Min Act: -0.0004

Data Index: 1058717 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0632. Min Act: 0.0001

Data Index: 1102610 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0613. Min Act: -0.0002

Data Index: 580716 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0595. Min Act: -0.0003

Data Index: 208298 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0601. Min Act: -0.0003

Data Index: 766530 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0606. Min Act: 0.0001

Data Index: 1578995 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0598. Min Act: -0.0001

Data Index: 415611 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0589. Min Act: -0.0001

Data Index: 524181 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1336707 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0583. Min Act: -0.0003

Data Index: 34509 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0597. Min Act: -0.0001

Data Index: 315120 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0577. Min Act: -0.0002

Data Index: 659659 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0585. Min Act: -0.0002

Data Index: 896369 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0577. Min Act: -0.0002

Data Index: 152483 (C4 (Web Text))

Max Activating Token Index: 1020