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

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

Neuron 714 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2428. Min Act: -0.0000

Data Index: 726084 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2183. Min Act: -0.0000

Data Index: 569526 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.2072. Min Act: -0.0000

Data Index: 904544 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1863. Min Act: -0.0000

Data Index: 252773 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1496265 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1479282 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1870. Min Act: -0.0000

Data Index: 381804 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1759. Min Act: -0.0000

Data Index: 963651 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1437525 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1005418 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1600241 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1409982 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1832. Min Act: -0.0000

Data Index: 231317 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1746. Min Act: -0.0000

Data Index: 969808 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1627548 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1657. Min Act: -0.0000

Data Index: 784379 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1769. Min Act: -0.0000

Data Index: 377606 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1528140 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1410781 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 0.2428. Min Range: -0.2428

Max Act: 0.1689. Min Act: -0.0000

Data Index: 721050 (C4 (Web Text))

Max Activating Token Index: 850