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

Dataset: The Pile

Neuron 5079 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: 1.0824. Min Range: -1.0824

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1508806 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1857072 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1886083 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8750. Min Act: -0.0000

Data Index: 191470 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9161. Min Act: -0.0000

Data Index: 510765 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8852. Min Act: -0.0000

Data Index: 279611 (The Pile)

Max Activating Token Index: 68

Text #6

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1985841 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1600973 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8742. Min Act: -0.0000

Data Index: 650357 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8287. Min Act: -0.0000

Data Index: 973588 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9111. Min Act: -0.0000

Data Index: 475195 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9115. Min Act: -0.0000

Data Index: 133816 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8663. Min Act: -0.0000

Data Index: 999889 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1833294 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1433567 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8439. Min Act: -0.0000

Data Index: 478652 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1559905 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1565029 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1331009 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1025441 (The Pile)

Max Activating Token Index: 521