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

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

Neuron 3349 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: 0.2152. Min Range: -0.2152

Max Act: 0.1929. Min Act: -0.0000

Data Index: 602406 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1888. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.2152. Min Act: -0.0000

Data Index: 40989 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1950. Min Act: -0.0000

Data Index: 44534 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1045955 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1948. Min Act: -0.0000

Data Index: 905701 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.2043. Min Act: -0.0000

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1959. Min Act: -0.0000

Data Index: 972928 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1872. Min Act: -0.0000

Data Index: 175574 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1606789 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1649626 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1396282 (Python Code)

Max Activating Token Index: 363

Text #12

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1640692 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1515977 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1432296 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1600. Min Act: -0.0000

Data Index: 610171 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1508234 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1644610 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1224071 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1494. Min Act: -0.0000

Data Index: 827554 (C4 (Web Text))

Max Activating Token Index: 133