Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1115496 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0002

Data Index: 778758 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0675. Min Act: -0.0002

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0690. Min Act: -0.0002

Data Index: 939076 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0668. Min Act: -0.0002

Data Index: 239940 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1190514 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0649. Min Act: -0.0002

Data Index: 473046 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0635. Min Act: -0.0002

Data Index: 792997 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0631. Min Act: -0.0002

Data Index: 582494 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0628. Min Act: -0.0002

Data Index: 328058 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1198257 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0626. Min Act: -0.0002

Data Index: 857376 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0605. Min Act: -0.0002

Data Index: 192824 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0620. Min Act: -0.0002

Data Index: 839249 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0598. Min Act: -0.0002

Data Index: 800 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0639. Min Act: -0.0002

Data Index: 370090 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0616. Min Act: -0.0002

Data Index: 205981 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0609. Min Act: -0.0002

Data Index: 601966 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0614. Min Act: -0.0002

Data Index: 844835 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1259454 (C4 (Web Text))

Max Activating Token Index: 546