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

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

Neuron 179 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: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 650012 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0838. Min Act: -0.0002

Data Index: 486866 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1327660 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0842. Min Act: -0.0002

Data Index: 880683 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0832. Min Act: -0.0002

Data Index: 160226 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1002765 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0822. Min Act: -0.0002

Data Index: 782768 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0794. Min Act: -0.0002

Data Index: 743791 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0785. Min Act: -0.0002

Data Index: 350329 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0766. Min Act: -0.0002

Data Index: 741610 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0745. Min Act: -0.0002

Data Index: 14103 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0746. Min Act: -0.0002

Data Index: 557983 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0737. Min Act: -0.0002

Data Index: 835219 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0745. Min Act: -0.0002

Data Index: 481901 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0759. Min Act: -0.0002

Data Index: 443025 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0744. Min Act: -0.0002

Data Index: 840329 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0734. Min Act: -0.0002

Data Index: 689305 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1068379 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1326592 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0698. Min Act: -0.0002

Data Index: 914581 (C4 (Web Text))

Max Activating Token Index: 796