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

Dataset: The Pile

Neuron 3339 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: 0.1094. Min Range: -0.1094

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1165362 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0985. Min Act: -0.0000

Data Index: 64482 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1510082 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0864. Min Act: -0.0000

Data Index: 3373 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0807. Min Act: -0.0000

Data Index: 300615 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1242721 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1387325 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1626428 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0812. Min Act: -0.0000

Data Index: 533232 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0766. Min Act: -0.0000

Data Index: 814041 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0731. Min Act: -0.0000

Data Index: 897291 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0753. Min Act: -0.0000

Data Index: 731433 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0806. Min Act: -0.0000

Data Index: 445561 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0743. Min Act: -0.0000

Data Index: 760338 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1986929 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0723. Min Act: -0.0000

Data Index: 234010 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0702. Min Act: -0.0000

Data Index: 261717 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0706. Min Act: -0.0000

Data Index: 508239 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1070214 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.1094. Min Range: -0.1094

Max Act: 0.0692. Min Act: -0.0000

Data Index: 911354 (The Pile)

Max Activating Token Index: 959