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

Dataset: The Pile

Neuron 2216 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: 1.9017. Min Range: -1.9017

Max Act: 1.9017. Min Act: -0.0000

Data Index: 1749160 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.4371. Min Act: -0.0000

Data Index: 978722 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1055301 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1746138 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.2284. Min Act: -0.0000

Data Index: 391348 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1707. Min Act: -0.0000

Data Index: 249310 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1893. Min Act: -0.0000

Data Index: 208920 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1988118 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1115763 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1282494 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1776. Min Act: 0.0000

Data Index: 1289195 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1425. Min Act: -0.0000

Data Index: 916782 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1436. Min Act: -0.0000

Data Index: 171526 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1728. Min Act: 0.0000

Data Index: 1554096 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.2076. Min Act: -0.0000

Data Index: 186641 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1867680 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1053226 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1767. Min Act: 0.0000

Data Index: 653541 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1044281 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.9017. Min Range: -1.9017

Max Act: 1.1584. Min Act: 0.0000

Data Index: 249801 (The Pile)

Max Activating Token Index: 33