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

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

Neuron 3625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1308082 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1990. Min Act: -0.0000

Data Index: 442649 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2062. Min Act: -0.0000

Data Index: 143826 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.2007. Min Act: -0.0000

Data Index: 556044 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1796. Min Act: -0.0000

Data Index: 957219 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1699. Min Act: -0.0000

Data Index: 110824 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1735. Min Act: -0.0000

Data Index: 377000 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1109683 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1821. Min Act: -0.0000

Data Index: 443310 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1342796 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1042539 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1346130 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1257975 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1618. Min Act: -0.0000

Data Index: 501827 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1625. Min Act: -0.0000

Data Index: 437921 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1082870 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1660. Min Act: -0.0000

Data Index: 556238 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1539. Min Act: -0.0000

Data Index: 221419 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1578. Min Act: -0.0000

Data Index: 594371 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.2622. Min Range: -0.2622

Max Act: 0.1581. Min Act: -0.0000

Data Index: 923137 (C4 (Web Text))

Max Activating Token Index: 217