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

Dataset: The Pile

Neuron 4683 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6648. Min Act: -0.0000

Data Index: 678167 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1922556 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1364547 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5599. Min Act: -0.0000

Data Index: 231649 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5484. Min Act: -0.0000

Data Index: 842113 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5653. Min Act: -0.0000

Data Index: 899888 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1393017 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5207. Min Act: -0.0000

Data Index: 417550 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5375. Min Act: -0.0000

Data Index: 453001 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1127715 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1733663 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1789866 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1591874 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.5129. Min Act: -0.0000

Data Index: 494842 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4786. Min Act: -0.0000

Data Index: 908101 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4916. Min Act: -0.0000

Data Index: 986370 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4747. Min Act: -0.0000

Data Index: 135823 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4864. Min Act: -0.0000

Data Index: 517775 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1146094 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 0.6648. Min Range: -0.6648

Max Act: 0.4967. Min Act: -0.0000

Data Index: 759784 (The Pile)

Max Activating Token Index: 722