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

Dataset: The Pile

Neuron 3324 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0000

Data Index: 47366 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1230694 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1649549 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1811481 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1072558 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8976. Min Act: -0.0000

Data Index: 514001 (The Pile)

Max Activating Token Index: 105

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1422613 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7504. Min Act: -0.0000

Data Index: 34846 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1340488 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1246957 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1052228 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8644. Min Act: -0.0000

Data Index: 577658 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8222. Min Act: -0.0000

Data Index: 697737 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1067143 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8935. Min Act: -0.0000

Data Index: 955273 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8135. Min Act: -0.0000

Data Index: 808498 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1661047 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7789. Min Act: -0.0000

Data Index: 989050 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1752600 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8380. Min Act: -0.0000

Data Index: 897631 (The Pile)

Max Activating Token Index: 209