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

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

Neuron 3646 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: 1.1628. Min Range: -1.1628

Max Act: 1.1074. Min Act: -0.0002

Data Index: 187746 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1463. Min Act: -0.0002

Data Index: 716090 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1628. Min Act: -0.0002

Data Index: 1292885 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0611. Min Act: -0.0002

Data Index: 1222554 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1604. Min Act: -0.0002

Data Index: 502656 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0762. Min Act: -0.0002

Data Index: 1038790 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0703. Min Act: -0.0002

Data Index: 618017 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0690. Min Act: -0.0002

Data Index: 736947 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0972. Min Act: -0.0002

Data Index: 402407 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0322. Min Act: -0.0002

Data Index: 891052 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0565. Min Act: -0.0002

Data Index: 512799 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0863. Min Act: -0.0002

Data Index: 126507 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0540. Min Act: -0.0002

Data Index: 1219977 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0822. Min Act: -0.0002

Data Index: 1173248 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0329. Min Act: -0.0002

Data Index: 917570 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0291. Min Act: -0.0002

Data Index: 315621 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0193. Min Act: -0.0002

Data Index: 870954 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9983. Min Act: -0.0002

Data Index: 1162195 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0224. Min Act: -0.0002

Data Index: 933889 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9928. Min Act: -0.0002

Data Index: 812431 (C4 (Web Text))

Max Activating Token Index: 32