Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1274082 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2266. Min Act: -0.0000

Data Index: 54505 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2033. Min Act: -0.0000

Data Index: 454067 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2010. Min Act: -0.0000

Data Index: 495790 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2001. Min Act: -0.0000

Data Index: 653110 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1621333 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2016. Min Act: -0.0000

Data Index: 378656 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1339464 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1868. Min Act: -0.0000

Data Index: 831816 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1811. Min Act: -0.0000

Data Index: 373572 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1876. Min Act: -0.0000

Data Index: 363490 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1714. Min Act: -0.0000

Data Index: 976918 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1696. Min Act: -0.0000

Data Index: 773651 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1621432 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1666. Min Act: -0.0000

Data Index: 548273 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1450277 (Python Code)

Max Activating Token Index: 715

Text #16

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1677. Min Act: -0.0000

Data Index: 2871 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1567. Min Act: -0.0000

Data Index: 713430 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1497. Min Act: -0.0000

Data Index: 948396 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1649. Min Act: -0.0000

Data Index: 998734 (C4 (Web Text))

Max Activating Token Index: 413