Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.4903. Min Act: -0.0002

Data Index: 764344 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.2578. Min Act: -0.0002

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1349. Min Act: -0.0002

Data Index: 235730 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.1936. Min Act: -0.0002

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0574. Min Act: -0.0002

Data Index: 1287135 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0662. Min Act: -0.0002

Data Index: 652988 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0132. Min Act: -0.0002

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9752. Min Act: -0.0001

Data Index: 686540 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.4903. Min Range: -1.4903

Max Act: 1.0263. Min Act: -0.0001

Data Index: 1007613 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9749. Min Act: -0.0002

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9360. Min Act: -0.0001

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9603. Min Act: -0.0002

Data Index: 1025558 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9101. Min Act: -0.0001

Data Index: 1068831 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8759. Min Act: -0.0001

Data Index: 54075 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8093. Min Act: -0.0001

Data Index: 1178701 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8444. Min Act: -0.0002

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8738. Min Act: -0.0001

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.9205. Min Act: -0.0002

Data Index: 292691 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.7842. Min Act: -0.0002

Data Index: 1061458 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 1.4903. Min Range: -1.4903

Max Act: 0.8040. Min Act: -0.0002

Data Index: 1180609 (C4 (Web Text))

Max Activating Token Index: 282