Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1568 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2518. Min Act: -0.0002

Data Index: 868748 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2297. Min Act: -0.0002

Data Index: 698285 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1926. Min Act: -0.0002

Data Index: 639048 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1988. Min Act: -0.0002

Data Index: 1194386 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1228034 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1807. Min Act: -0.0002

Data Index: 236673 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2012. Min Act: -0.0002

Data Index: 135381 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1926. Min Act: -0.0002

Data Index: 389186 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1797. Min Act: -0.0002

Data Index: 1359836 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1851. Min Act: -0.0002

Data Index: 928377 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1840. Min Act: -0.0002

Data Index: 983795 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1191756 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1774. Min Act: -0.0002

Data Index: 384921 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1804. Min Act: -0.0002

Data Index: 1271014 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1495. Min Act: -0.0002

Data Index: 234949 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1658. Min Act: -0.0002

Data Index: 1152259 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1735. Min Act: -0.0002

Data Index: 786424 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1669. Min Act: -0.0002

Data Index: 289916 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1726. Min Act: -0.0002

Data Index: 485067 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1642. Min Act: -0.0002

Data Index: 176007 (C4 (Web Text))

Max Activating Token Index: 468