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

Dataset: The Pile

Neuron 4900 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.7745. Min Range: -5.7745

Max Act: 5.7745. Min Act: -0.0000

Data Index: 1821330 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 5.7745. Min Range: -5.7745

Max Act: 5.1849. Min Act: -0.0000

Data Index: 585883 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 5.7745. Min Range: -5.7745

Max Act: 5.0006. Min Act: -0.0000

Data Index: 761381 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 5.7745. Min Range: -5.7745

Max Act: 5.1029. Min Act: -0.0000

Data Index: 1203181 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.8883. Min Act: -0.0000

Data Index: 917108 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.8772. Min Act: -0.0000

Data Index: 580858 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.6739. Min Act: -0.0000

Data Index: 323230 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.3406. Min Act: -0.0000

Data Index: 831179 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.2273. Min Act: -0.0000

Data Index: 1074718 (The Pile)

Max Activating Token Index: 362

Text #9

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.4208. Min Act: -0.0000

Data Index: 553978 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.0413. Min Act: -0.0000

Data Index: 966008 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.0125. Min Act: -0.0000

Data Index: 1577138 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.1513. Min Act: -0.0000

Data Index: 1744899 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 5.7745. Min Range: -5.7745

Max Act: 3.9290. Min Act: -0.0000

Data Index: 825403 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.0417. Min Act: -0.0000

Data Index: 831123 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.0596. Min Act: -0.0000

Data Index: 1653396 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.1803. Min Act: -0.0000

Data Index: 389061 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 5.7745. Min Range: -5.7745

Max Act: 3.8108. Min Act: -0.0000

Data Index: 900814 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 5.7745. Min Range: -5.7745

Max Act: 3.9419. Min Act: -0.0000

Data Index: 1142821 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 5.7745. Min Range: -5.7745

Max Act: 4.0534. Min Act: -0.0000

Data Index: 1813609 (The Pile)

Max Activating Token Index: 761