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

Dataset: The Pile

Neuron 4605 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1811476 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0000

Data Index: 311975 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1595. Min Act: -0.0000

Data Index: 642289 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2680. Min Act: -0.0000

Data Index: 965300 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1661333 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1178973 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1901437 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1667. Min Act: -0.0000

Data Index: 247764 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0810. Min Act: -0.0000

Data Index: 966730 (The Pile)

Max Activating Token Index: 132

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1264. Min Act: -0.0000

Data Index: 810760 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2257. Min Act: -0.0000

Data Index: 550612 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1746491 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0662. Min Act: -0.0000

Data Index: 824479 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1602. Min Act: -0.0000

Data Index: 142436 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1956582 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0778. Min Act: -0.0000

Data Index: 11363 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1218. Min Act: -0.0000

Data Index: 685978 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1198631 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1487. Min Act: -0.0000

Data Index: 286097 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0602. Min Act: -0.0000

Data Index: 875880 (The Pile)

Max Activating Token Index: 890