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

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

Neuron 4081 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: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0002

Data Index: 788142 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0851. Min Act: -0.0002

Data Index: 106022 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0813. Min Act: -0.0002

Data Index: 885727 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0679. Min Act: -0.0002

Data Index: 160199 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0551. Min Act: -0.0002

Data Index: 847905 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1421288 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1340548 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1634372 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0605. Min Act: -0.0002

Data Index: 530509 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0701. Min Act: -0.0002

Data Index: 414449 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0645. Min Act: -0.0002

Data Index: 424917 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0677. Min Act: -0.0002

Data Index: 539519 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0705. Min Act: -0.0002

Data Index: 862029 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0593. Min Act: -0.0002

Data Index: 291465 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0518. Min Act: -0.0002

Data Index: 207355 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0643. Min Act: -0.0002

Data Index: 974364 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1004249 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0585. Min Act: -0.0002

Data Index: 172234 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1273121 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1628088 (Python Code)

Max Activating Token Index: 667