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

Dataset: The Pile

Neuron 4110 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1489338 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1162533 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1954056 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1857601 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1598140 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2100. Min Act: -0.0000

Data Index: 932859 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2015. Min Act: -0.0000

Data Index: 287697 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1662060 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1428779 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1825156 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1959. Min Act: -0.0000

Data Index: 981136 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1438553 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1607. Min Act: -0.0000

Data Index: 368134 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1631785 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1149264 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1630. Min Act: -0.0000

Data Index: 746854 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1754. Min Act: -0.0000

Data Index: 623430 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1728. Min Act: -0.0000

Data Index: 39279 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1713. Min Act: -0.0000

Data Index: 733170 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1929974 (The Pile)

Max Activating Token Index: 347