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

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

Neuron 2015 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1928. Min Act: -0.0002

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.2023. Min Act: -0.0002

Data Index: 1209332 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1998. Min Act: -0.0002

Data Index: 1139236 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1906. Min Act: -0.0002

Data Index: 898720 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1112490 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1609. Min Act: -0.0002

Data Index: 272086 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1694. Min Act: -0.0002

Data Index: 253032 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1621. Min Act: -0.0002

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1541. Min Act: -0.0002

Data Index: 418693 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1492. Min Act: -0.0002

Data Index: 248498 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1539. Min Act: -0.0002

Data Index: 1192195 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1654. Min Act: -0.0002

Data Index: 848610 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1551. Min Act: -0.0002

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1608. Min Act: -0.0002

Data Index: 265774 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1470. Min Act: -0.0002

Data Index: 735547 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1423. Min Act: -0.0002

Data Index: 1116332 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1277458 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1380. Min Act: -0.0002

Data Index: 946810 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.2023. Min Range: -0.2023

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1355562 (C4 (Web Text))

Max Activating Token Index: 769