Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0806. Min Act: -0.0001

Data Index: 500900 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0790. Min Act: -0.0002

Data Index: 429678 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1235418 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0783. Min Act: -0.0002

Data Index: 808963 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0770. Min Act: -0.0002

Data Index: 666071 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0797. Min Act: -0.0002

Data Index: 4415 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0733. Min Act: -0.0001

Data Index: 620791 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0712. Min Act: -0.0001

Data Index: 368185 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0757. Min Act: -0.0002

Data Index: 83319 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0705. Min Act: -0.0001

Data Index: 222186 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0705. Min Act: -0.0002

Data Index: 358652 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0714. Min Act: -0.0002

Data Index: 13489 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0710. Min Act: -0.0002

Data Index: 156718 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1001145 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0717. Min Act: -0.0002

Data Index: 948533 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0706. Min Act: -0.0002

Data Index: 205965 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0686. Min Act: -0.0002

Data Index: 649826 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1319017 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0696. Min Act: -0.0002

Data Index: 518141 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0806. Min Range: -0.0806

Max Act: 0.0680. Min Act: -0.0002

Data Index: 534398 (C4 (Web Text))

Max Activating Token Index: 640