Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1877. Min Act: -0.0003

Data Index: 405445 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0004

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1765. Min Act: -0.0003

Data Index: 459822 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1793. Min Act: -0.0003

Data Index: 639153 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1767. Min Act: -0.0003

Data Index: 819844 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1833. Min Act: -0.0003

Data Index: 317264 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1775. Min Act: -0.0003

Data Index: 1270024 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1721. Min Act: -0.0003

Data Index: 1142748 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1776. Min Act: -0.0004

Data Index: 615818 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1590. Min Act: -0.0003

Data Index: 230815 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1708. Min Act: -0.0003

Data Index: 87425 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1684. Min Act: -0.0003

Data Index: 1339686 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1643. Min Act: -0.0004

Data Index: 1127781 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1772. Min Act: -0.0003

Data Index: 570730 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1759. Min Act: -0.0003

Data Index: 26739 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1660. Min Act: -0.0003

Data Index: 49743 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1622. Min Act: -0.0004

Data Index: 757611 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1593. Min Act: -0.0003

Data Index: 974128 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1602. Min Act: -0.0003

Data Index: 1275304 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1655. Min Act: -0.0003

Data Index: 971071 (C4 (Web Text))

Max Activating Token Index: 791