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

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

Neuron 4690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0001

Data Index: 815773 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0945. Min Act: -0.0000

Data Index: 499599 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1222541 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0844. Min Act: -0.0001

Data Index: 983396 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0867. Min Act: -0.0000

Data Index: 28918 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0870. Min Act: -0.0000

Data Index: 645286 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0803. Min Act: -0.0001

Data Index: 404814 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1272639 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1325717 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1246073 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0794. Min Act: -0.0000

Data Index: 785215 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0760. Min Act: -0.0000

Data Index: 605780 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1318237 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1091727 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0719. Min Act: -0.0001

Data Index: 838623 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0717. Min Act: -0.0001

Data Index: 111767 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0686. Min Act: -0.0000

Data Index: 719346 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0793. Min Act: -0.0000

Data Index: 496454 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0732. Min Act: -0.0000

Data Index: 245849 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0732. Min Act: -0.0000

Data Index: 41096 (C4 (Web Text))

Max Activating Token Index: 21