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

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

Neuron 1389 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0005

Data Index: 1013813 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1904. Min Act: -0.0005

Data Index: 1314182 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1906. Min Act: -0.0005

Data Index: 468555 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1679. Min Act: -0.0005

Data Index: 365112 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1614. Min Act: -0.0005

Data Index: 524256 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1654. Min Act: -0.0005

Data Index: 831466 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1859. Min Act: -0.0005

Data Index: 208257 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1693. Min Act: -0.0005

Data Index: 912007 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1635. Min Act: -0.0005

Data Index: 435842 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1774. Min Act: -0.0005

Data Index: 1077205 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1594. Min Act: -0.0005

Data Index: 16802 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1643. Min Act: -0.0005

Data Index: 320078 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1699. Min Act: -0.0005

Data Index: 1111688 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1628. Min Act: -0.0005

Data Index: 136324 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1801. Min Act: -0.0005

Data Index: 831267 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1736. Min Act: -0.0005

Data Index: 1246317 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1672. Min Act: -0.0005

Data Index: 210347 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1796. Min Act: -0.0005

Data Index: 412527 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1669. Min Act: -0.0005

Data Index: 1228397 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1903. Min Act: -0.0005

Data Index: 785007 (C4 (Web Text))

Max Activating Token Index: 652