Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 236 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1984. Min Act: -0.0003

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1904. Min Act: -0.0003

Data Index: 838641 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1777. Min Act: -0.0003

Data Index: 380250 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1783. Min Act: -0.0003

Data Index: 698480 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1848. Min Act: -0.0003

Data Index: 72377 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1779. Min Act: -0.0003

Data Index: 489620 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1743. Min Act: -0.0003

Data Index: 552160 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1798. Min Act: -0.0003

Data Index: 791639 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1828. Min Act: -0.0003

Data Index: 1016507 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1763. Min Act: -0.0003

Data Index: 693650 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1753. Min Act: -0.0003

Data Index: 207630 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1756. Min Act: -0.0003

Data Index: 1025117 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1672. Min Act: -0.0003

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1650. Min Act: -0.0003

Data Index: 1520792 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1695. Min Act: -0.0003

Data Index: 646418 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1439. Min Act: -0.0003

Data Index: 884215 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1715. Min Act: -0.0003

Data Index: 616350 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1598. Min Act: -0.0002

Data Index: 1136532 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1534. Min Act: -0.0003

Data Index: 1164897 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.1984. Min Range: -0.1984

Max Act: 0.1508. Min Act: -0.0003

Data Index: 961075 (C4 (Web Text))

Max Activating Token Index: 548