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

Dataset: The Pile

Neuron 1451 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1688292 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1795588 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5233. Min Act: -0.0000

Data Index: 416876 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5195. Min Act: -0.0000

Data Index: 552888 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1286057 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1471775 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4948. Min Act: -0.0000

Data Index: 116399 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5094. Min Act: -0.0000

Data Index: 319706 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1624841 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1469055 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1520400 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4694. Min Act: -0.0001

Data Index: 1195429 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1472473 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4856. Min Act: -0.0000

Data Index: 352983 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5617. Min Act: -0.0000

Data Index: 572826 (The Pile)

Max Activating Token Index: 474

Text #15

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4941. Min Act: -0.0000

Data Index: 502038 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4798. Min Act: -0.0000

Data Index: 698125 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4757. Min Act: -0.0000

Data Index: 909232 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4841. Min Act: -0.0000

Data Index: 936185 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1494165 (The Pile)

Max Activating Token Index: 610