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

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

Neuron 2111 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: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0001

Data Index: 528917 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0830. Min Act: -0.0001

Data Index: 766409 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0783. Min Act: -0.0002

Data Index: 432164 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0806. Min Act: -0.0001

Data Index: 70841 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1324462 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0759. Min Act: -0.0001

Data Index: 183496 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0754. Min Act: -0.0001

Data Index: 25981 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0783. Min Act: -0.0002

Data Index: 5272 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0769. Min Act: -0.0002

Data Index: 20961 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0742. Min Act: -0.0002

Data Index: 814536 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0755. Min Act: -0.0001

Data Index: 651428 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1221871 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1084304 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1136848 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0730. Min Act: -0.0001

Data Index: 569381 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1212960 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0730. Min Act: -0.0001

Data Index: 474486 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0694. Min Act: -0.0002

Data Index: 110952 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0642. Min Act: -0.0001

Data Index: 461750 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0692. Min Act: -0.0001

Data Index: 695813 (C4 (Web Text))

Max Activating Token Index: 334