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

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

Neuron 4564 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: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0002

Data Index: 360019 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0746. Min Act: -0.0002

Data Index: 131816 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0700. Min Act: -0.0002

Data Index: 100452 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0680. Min Act: -0.0002

Data Index: 959175 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0675. Min Act: -0.0002

Data Index: 35020 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0670. Min Act: -0.0002

Data Index: 189661 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1055249 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0646. Min Act: -0.0002

Data Index: 33541 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1227501 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0653. Min Act: -0.0002

Data Index: 43873 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0624. Min Act: -0.0002

Data Index: 569964 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1111132 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0592. Min Act: -0.0002

Data Index: 346436 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1138796 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0602. Min Act: -0.0002

Data Index: 225353 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0595. Min Act: -0.0002

Data Index: 191667 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1179189 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1002992 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1075921 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1344328 (C4 (Web Text))

Max Activating Token Index: 669