Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2798 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1906275 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.2999. Min Act: -0.0000

Data Index: 565059 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1980662 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1606. Min Act: -0.0000

Data Index: 15531 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1389. Min Act: -0.0000

Data Index: 396473 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1878247 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1955240 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1093465 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1292153 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1695. Min Act: -0.0000

Data Index: 812664 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0185. Min Act: -0.0000

Data Index: 114908 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1759015 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1966931 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1409557 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1041. Min Act: -0.0000

Data Index: 467277 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1410188 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1859470 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0191. Min Act: -0.0000

Data Index: 475507 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0083. Min Act: -0.0000

Data Index: 768418 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9933. Min Act: -0.0000

Data Index: 213832 (The Pile)

Max Activating Token Index: 464