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

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

Neuron 500 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: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0003

Data Index: 603840 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0961. Min Act: -0.0004

Data Index: 1210736 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0931. Min Act: -0.0003

Data Index: 691984 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0934. Min Act: -0.0003

Data Index: 1163238 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0891. Min Act: -0.0003

Data Index: 803292 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0869. Min Act: -0.0004

Data Index: 967980 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0869. Min Act: -0.0003

Data Index: 1193298 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0833. Min Act: -0.0003

Data Index: 821663 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0849. Min Act: -0.0003

Data Index: 1345692 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0838. Min Act: -0.0003

Data Index: 704010 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0837. Min Act: -0.0003

Data Index: 400177 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0831. Min Act: -0.0003

Data Index: 1053161 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0802. Min Act: -0.0003

Data Index: 21285 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0826. Min Act: -0.0003

Data Index: 313662 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0822. Min Act: -0.0003

Data Index: 909635 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0792. Min Act: -0.0003

Data Index: 186572 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0788. Min Act: -0.0003

Data Index: 93266 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0810. Min Act: -0.0004

Data Index: 622515 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0793. Min Act: -0.0003

Data Index: 1264628 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0773. Min Act: -0.0003

Data Index: 138544 (C4 (Web Text))

Max Activating Token Index: 69