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

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

Neuron 683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0003

Data Index: 204758 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0723. Min Act: -0.0003

Data Index: 332142 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0725. Min Act: -0.0003

Data Index: 433866 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1612524 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1405982 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0656. Min Act: -0.0003

Data Index: 776341 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1422443 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0649. Min Act: -0.0003

Data Index: 279418 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0651. Min Act: -0.0003

Data Index: 627466 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1560925 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1539845 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0640. Min Act: -0.0004

Data Index: 1603044 (Python Code)

Max Activating Token Index: 192

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1554966 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1568839 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1423222 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0629. Min Act: -0.0004

Data Index: 1636564 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1083740 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1458694 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1521501 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0599. Min Act: -0.0003

Data Index: 569387 (C4 (Web Text))

Max Activating Token Index: 35