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

Dataset: The Pile

Neuron 4983 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: 5.4635. Min Range: -5.4635

Max Act: 5.4635. Min Act: -0.0000

Data Index: 711317 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 5.4635. Min Range: -5.4635

Max Act: 5.2038. Min Act: -0.0000

Data Index: 1084323 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 5.4635. Min Range: -5.4635

Max Act: 4.7311. Min Act: -0.0000

Data Index: 1788303 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 5.4635. Min Range: -5.4635

Max Act: 4.4534. Min Act: -0.0000

Data Index: 1727325 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 5.4635. Min Range: -5.4635

Max Act: 4.1806. Min Act: -0.0000

Data Index: 472769 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.8665. Min Act: -0.0000

Data Index: 1442186 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.8552. Min Act: -0.0000

Data Index: 335988 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.3711. Min Act: -0.0000

Data Index: 1820344 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.5788. Min Act: -0.0000

Data Index: 1471349 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.6811. Min Act: 0.0000

Data Index: 1056526 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.2655. Min Act: -0.0000

Data Index: 1977876 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.2974. Min Act: -0.0000

Data Index: 1264984 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.4394. Min Act: -0.0000

Data Index: 932058 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.3070. Min Act: -0.0000

Data Index: 494390 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.2078. Min Act: -0.0000

Data Index: 13968 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.0079. Min Act: -0.0000

Data Index: 1174299 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 5.4635. Min Range: -5.4635

Max Act: 3.9141. Min Act: -0.0000

Data Index: 1904828 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 5.4635. Min Range: -5.4635

Max Act: 2.5229. Min Act: -0.0000

Data Index: 1155837 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 5.4635. Min Range: -5.4635

Max Act: 2.9772. Min Act: -0.0000

Data Index: 564668 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 5.4635. Min Range: -5.4635

Max Act: 2.9563. Min Act: -0.0000

Data Index: 1351250 (The Pile)

Max Activating Token Index: 432