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

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

Neuron 3235 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: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0002

Data Index: 585574 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1306108 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1240060 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0753. Min Act: -0.0002

Data Index: 437767 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0765. Min Act: -0.0002

Data Index: 137477 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0829. Min Act: -0.0002

Data Index: 892615 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1198530 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1236655 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0747. Min Act: -0.0002

Data Index: 370064 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0628. Min Act: -0.0002

Data Index: 278446 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0634. Min Act: -0.0002

Data Index: 761163 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1073908 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0675. Min Act: -0.0002

Data Index: 169165 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0727. Min Act: -0.0002

Data Index: 45058 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1029935 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0721. Min Act: -0.0002

Data Index: 134176 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0772. Min Act: -0.0002

Data Index: 174822 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0664. Min Act: -0.0002

Data Index: 273382 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0665. Min Act: -0.0002

Data Index: 31536 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0590. Min Act: -0.0002

Data Index: 869224 (C4 (Web Text))

Max Activating Token Index: 905