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

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

Neuron 1315 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: 0.1018. Min Range: -0.1018

Max Act: 0.1018. Min Act: -0.0002

Data Index: 155021 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0928. Min Act: -0.0002

Data Index: 117319 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0924. Min Act: -0.0002

Data Index: 524399 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0929. Min Act: -0.0002

Data Index: 968552 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0934. Min Act: -0.0003

Data Index: 458278 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0840. Min Act: -0.0002

Data Index: 169441 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0835. Min Act: -0.0003

Data Index: 324187 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0853. Min Act: -0.0003

Data Index: 718191 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0856. Min Act: -0.0003

Data Index: 310961 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1319384 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1199434 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0828. Min Act: -0.0002

Data Index: 47670 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0826. Min Act: -0.0002

Data Index: 691554 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0795. Min Act: -0.0002

Data Index: 247898 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0815. Min Act: -0.0003

Data Index: 982481 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0783. Min Act: -0.0002

Data Index: 565402 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1266817 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0769. Min Act: -0.0002

Data Index: 710225 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1099545 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.1018. Min Range: -0.1018

Max Act: 0.0770. Min Act: -0.0002

Data Index: 436537 (C4 (Web Text))

Max Activating Token Index: 600