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

Dataset: The Pile

Neuron 4573 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: 0.2735. Min Range: -0.2735

Max Act: 0.2504. Min Act: -0.0000

Data Index: 462815 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2735. Min Act: -0.0000

Data Index: 374067 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2281. Min Act: -0.0000

Data Index: 404876 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1765911 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2150. Min Act: -0.0000

Data Index: 173211 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2145. Min Act: -0.0000

Data Index: 852733 (The Pile)

Max Activating Token Index: 416

Text #6

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1041239 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1610035 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1990. Min Act: -0.0000

Data Index: 15508 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1570006 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1883. Min Act: -0.0000

Data Index: 684386 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1531549 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1045462 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1292394 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1830207 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1921. Min Act: -0.0000

Data Index: 297895 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1120978 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1073482 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1734319 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1207945 (The Pile)

Max Activating Token Index: 255