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

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

Neuron 3206 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1122210 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1301155 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0640. Min Act: -0.0001

Data Index: 813526 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0614. Min Act: -0.0001

Data Index: 616102 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0615. Min Act: -0.0001

Data Index: 701488 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0633. Min Act: -0.0000

Data Index: 82699 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0547. Min Act: -0.0001

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0578. Min Act: -0.0001

Data Index: 563742 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0603. Min Act: -0.0000

Data Index: 992196 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0563. Min Act: -0.0001

Data Index: 320909 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0565. Min Act: -0.0001

Data Index: 760205 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0556. Min Act: -0.0001

Data Index: 499887 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1261431 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1147347 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0535. Min Act: -0.0001

Data Index: 44010 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0532. Min Act: -0.0001

Data Index: 465244 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0528. Min Act: -0.0001

Data Index: 966736 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1298160 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1602370 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0537. Min Act: -0.0001

Data Index: 356405 (C4 (Web Text))

Max Activating Token Index: 38