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

Dataset: The Pile

Neuron 550 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: 1.1811. Min Range: -1.1811

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1206883 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0303. Min Act: -0.0000

Data Index: 176494 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1267736 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0521. Min Act: -0.0000

Data Index: 346563 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1988684 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1368847 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0168. Min Act: -0.0000

Data Index: 646002 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0281. Min Act: -0.0000

Data Index: 547682 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1121955 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1852252 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9298. Min Act: -0.0000

Data Index: 433924 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1643524 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9041. Min Act: -0.0000

Data Index: 211498 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1455648 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8941. Min Act: -0.0000

Data Index: 729832 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1418212 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8705. Min Act: -0.0000

Data Index: 1338580 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8343. Min Act: -0.0000

Data Index: 834936 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1662170 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1492005 (The Pile)

Max Activating Token Index: 326