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

Dataset: The Pile

Neuron 1163 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: 3.2044. Min Range: -3.2044

Max Act: 3.1915. Min Act: -0.0000

Data Index: 1854894 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1980. Min Act: -0.0000

Data Index: 1773647 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1247. Min Act: -0.0000

Data Index: 322097 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.2044. Min Act: -0.0000

Data Index: 767976 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6847. Min Act: -0.0000

Data Index: 1427258 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.9100. Min Act: -0.0000

Data Index: 75936 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.7059. Min Act: -0.0000

Data Index: 1323697 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.8355. Min Act: -0.0000

Data Index: 1881112 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0657. Min Act: -0.0000

Data Index: 368969 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6255. Min Act: -0.0000

Data Index: 413172 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.7608. Min Act: -0.0000

Data Index: 594918 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.7798. Min Act: -0.0000

Data Index: 323176 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6479. Min Act: -0.0000

Data Index: 10832 (The Pile)

Max Activating Token Index: 844

Text #13

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.7182. Min Act: -0.0000

Data Index: 463593 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.5634. Min Act: -0.0000

Data Index: 227831 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.9772. Min Act: -0.0000

Data Index: 1446992 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.4136. Min Act: -0.0000

Data Index: 1751342 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6642. Min Act: -0.0000

Data Index: 125933 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6676. Min Act: -0.0000

Data Index: 1925981 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 3.2044. Min Range: -3.2044

Max Act: 2.6086. Min Act: -0.0000

Data Index: 345324 (The Pile)

Max Activating Token Index: 746