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

Dataset: The Pile

Neuron 4052 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: 1.8355. Min Range: -1.8355

Max Act: 1.7496. Min Act: -0.0000

Data Index: 328745 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.8355. Min Act: -0.0000

Data Index: 1200652 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.5933. Min Act: -0.0000

Data Index: 698382 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.5927. Min Act: -0.0000

Data Index: 1770906 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1775182 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.5015. Min Act: -0.0000

Data Index: 713695 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.2760. Min Act: -0.0000

Data Index: 166342 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3543. Min Act: -0.0000

Data Index: 514500 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3898. Min Act: -0.0000

Data Index: 754760 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.4030. Min Act: -0.0000

Data Index: 933292 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1473373 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1597990 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1625970 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.1920. Min Act: -0.0000

Data Index: 335524 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1400034 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1154167 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1962756 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.4004. Min Act: -0.0000

Data Index: 313907 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1967947 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 1.8355. Min Range: -1.8355

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1035185 (The Pile)

Max Activating Token Index: 315