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

Dataset: The Pile

Neuron 23 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1768829 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6461. Min Act: -0.0000

Data Index: 416985 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6638. Min Act: -0.0000

Data Index: 305598 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5965. Min Act: -0.0000

Data Index: 276156 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1685797 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6036. Min Act: -0.0000

Data Index: 597052 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1427284 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5693. Min Act: -0.0000

Data Index: 199526 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1507614 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5632. Min Act: -0.0000

Data Index: 815801 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5253. Min Act: -0.0000

Data Index: 396341 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5198. Min Act: -0.0000

Data Index: 271256 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1013711 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1104820 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1738337 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5108. Min Act: -0.0000

Data Index: 638861 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4965. Min Act: -0.0000

Data Index: 244505 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4620. Min Act: -0.0000

Data Index: 963377 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4849. Min Act: -0.0000

Data Index: 419964 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4941. Min Act: -0.0000

Data Index: 236664 (The Pile)

Max Activating Token Index: 417