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

Dataset: The Pile

Neuron 2838 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.2678. Min Act: -0.0000

Data Index: 84523 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.2042. Min Act: -0.0000

Data Index: 1650110 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1860115 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1848. Min Act: -0.0000

Data Index: 351066 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1100737 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0397. Min Act: -0.0000

Data Index: 503986 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.1288. Min Act: -0.0000

Data Index: 1150122 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1148225 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0235. Min Act: -0.0000

Data Index: 418373 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 1.2678. Min Range: -1.2678

Max Act: 1.0194. Min Act: -0.0000

Data Index: 122739 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9895. Min Act: -0.0000

Data Index: 466673 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1770056 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9369. Min Act: -0.0000

Data Index: 105655 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1524559 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9545. Min Act: -0.0000

Data Index: 143067 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1717600 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.8173. Min Act: -0.0000

Data Index: 49702 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1639681 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1494018 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 1.2678. Min Range: -1.2678

Max Act: 0.8600. Min Act: -0.0000

Data Index: 630585 (The Pile)

Max Activating Token Index: 1007