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

Dataset: The Pile

Neuron 458 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0986. Min Act: -0.0000

Data Index: 726272 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1035255 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9833. Min Act: -0.0000

Data Index: 31556 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0246. Min Act: -0.0000

Data Index: 434817 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1932140 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0053. Min Act: -0.0000

Data Index: 765243 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9789. Min Act: -0.0000

Data Index: 513978 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8584. Min Act: -0.0000

Data Index: 356538 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1481262 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9413. Min Act: -0.0000

Data Index: 731614 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8879. Min Act: -0.0000

Data Index: 975550 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1646725 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9677. Min Act: -0.0000

Data Index: 16293 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9290. Min Act: -0.0000

Data Index: 19560 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9087. Min Act: 0.0000

Data Index: 520487 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1754706 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1656081 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8529. Min Act: -0.0000

Data Index: 911780 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1898425 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1515326 (The Pile)

Max Activating Token Index: 320