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

Dataset: The Pile

Neuron 99 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6838. Min Act: -0.0000

Data Index: 971397 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1081038 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5074. Min Act: -0.0000

Data Index: 586393 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5529. Min Act: -0.0000

Data Index: 248631 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1133232 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5249. Min Act: -0.0000

Data Index: 295419 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.5220. Min Act: -0.0000

Data Index: 454626 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4735. Min Act: -0.0000

Data Index: 151186 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4811. Min Act: -0.0000

Data Index: 449635 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4636. Min Act: -0.0000

Data Index: 945299 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1278496 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1104624 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4376. Min Act: -0.0000

Data Index: 533624 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1828813 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1379048 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4852. Min Act: -0.0000

Data Index: 965688 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4328. Min Act: -0.0000

Data Index: 803126 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4313. Min Act: -0.0000

Data Index: 574120 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1625051 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 0.6838. Min Range: -0.6838

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1695004 (The Pile)

Max Activating Token Index: 749