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

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

Neuron 3002 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1764. Min Act: -0.0001

Data Index: 573020 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.2065. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1313205 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1747. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1961. Min Act: -0.0001

Data Index: 384230 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1119589 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1908. Min Act: -0.0001

Data Index: 515663 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1834. Min Act: -0.0000

Data Index: 76697 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1860. Min Act: -0.0000

Data Index: 175034 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1827. Min Act: -0.0001

Data Index: 918331 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1002144 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1703. Min Act: -0.0001

Data Index: 92977 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1795. Min Act: -0.0001

Data Index: 92954 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1710. Min Act: -0.0001

Data Index: 573373 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1715. Min Act: -0.0000

Data Index: 152879 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1709. Min Act: -0.0001

Data Index: 174480 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1307397 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1714. Min Act: -0.0001

Data Index: 594313 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1651. Min Act: -0.0001

Data Index: 728411 (C4 (Web Text))

Max Activating Token Index: 558