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

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

Neuron 1411 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: 0.0860. Min Range: -0.0860

Max Act: 0.0818. Min Act: -0.0002

Data Index: 567487 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0835. Min Act: -0.0002

Data Index: 861257 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0002

Data Index: 389510 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0855. Min Act: -0.0002

Data Index: 585146 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1293564 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0815. Min Act: -0.0002

Data Index: 246877 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0839. Min Act: -0.0002

Data Index: 782913 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0844. Min Act: -0.0002

Data Index: 66496 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0828. Min Act: -0.0002

Data Index: 85363 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0825. Min Act: -0.0002

Data Index: 848493 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0816. Min Act: -0.0002

Data Index: 878589 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1334063 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1001863 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0803. Min Act: -0.0002

Data Index: 553203 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0837. Min Act: -0.0002

Data Index: 946440 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0817. Min Act: -0.0002

Data Index: 745686 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1315832 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0826. Min Act: -0.0002

Data Index: 22654 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0731. Min Act: -0.0002

Data Index: 426902 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1337014 (C4 (Web Text))

Max Activating Token Index: 901