Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1884. Min Act: -0.0001

Data Index: 799149 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1805. Min Act: -0.0000

Data Index: 812458 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1319583 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1793. Min Act: -0.0001

Data Index: 419478 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1041705 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1803. Min Act: -0.0001

Data Index: 21725 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1795. Min Act: -0.0001

Data Index: 40054 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1860. Min Act: -0.0001

Data Index: 852140 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1019138 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1847. Min Act: -0.0001

Data Index: 493932 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1749. Min Act: -0.0001

Data Index: 274874 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1693. Min Act: -0.0001

Data Index: 635975 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1798. Min Act: -0.0000

Data Index: 504739 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1009164 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1614. Min Act: -0.0000

Data Index: 415634 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1631. Min Act: -0.0000

Data Index: 784191 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1246144 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1727. Min Act: -0.0001

Data Index: 308814 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1733. Min Act: -0.0000

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.1909. Min Range: -0.1909

Max Act: 0.1664. Min Act: -0.0000

Data Index: 96824 (C4 (Web Text))

Max Activating Token Index: 516