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

Dataset: The Pile

Neuron 4311 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: 0.7322. Min Range: -0.7322

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1711597 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6775. Min Act: -0.0000

Data Index: 274651 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6770. Min Act: -0.0000

Data Index: 770239 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6341. Min Act: -0.0000

Data Index: 399785 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6251. Min Act: -0.0000

Data Index: 524195 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1428643 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6648. Min Act: -0.0000

Data Index: 503215 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5881. Min Act: 0.0000

Data Index: 1859377 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6179. Min Act: 0.0000

Data Index: 896570 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5706. Min Act: -0.0000

Data Index: 630942 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5072. Min Act: -0.0000

Data Index: 96278 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1548622 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1921214 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5886. Min Act: -0.0000

Data Index: 507555 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.4976. Min Act: -0.0000

Data Index: 453661 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1109313 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1059066 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1730101 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1290739 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.7322. Min Range: -0.7322

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1129967 (The Pile)

Max Activating Token Index: 639