Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0000

Data Index: 591973 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1105. Min Act: -0.0000

Data Index: 961822 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1141770 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1034836 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0780. Min Act: -0.0000

Data Index: 575844 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0735. Min Act: -0.0000

Data Index: 272762 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1353205 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0716. Min Act: -0.0000

Data Index: 737093 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0625. Min Act: -0.0000

Data Index: 696899 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1410996 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0643. Min Act: -0.0000

Data Index: 82535 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1125523 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0621. Min Act: -0.0000

Data Index: 57752 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0651. Min Act: -0.0000

Data Index: 939113 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1500413 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0612. Min Act: -0.0000

Data Index: 496164 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0608. Min Act: -0.0000

Data Index: 136368 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1276694 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0583. Min Act: -0.0000

Data Index: 731766 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0574. Min Act: -0.0000

Data Index: 489315 (The Pile)

Max Activating Token Index: 980