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

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

Neuron 2203 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1869. Min Act: -0.0000

Data Index: 91117 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1779. Min Act: -0.0000

Data Index: 178939 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1185094 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0000

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1305754 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1843. Min Act: -0.0000

Data Index: 392015 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1069406 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1762. Min Act: -0.0000

Data Index: 79436 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1675. Min Act: -0.0000

Data Index: 185920 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1252989 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1541. Min Act: -0.0000

Data Index: 154380 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1041573 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1328759 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1603. Min Act: -0.0000

Data Index: 6122 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1531. Min Act: -0.0000

Data Index: 400964 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1515. Min Act: -0.0000

Data Index: 636722 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1492. Min Act: -0.0000

Data Index: 459310 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1338689 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1351. Min Act: -0.0000

Data Index: 823680 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1546. Min Act: -0.0000

Data Index: 434300 (C4 (Web Text))

Max Activating Token Index: 910