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

Dataset: The Pile

Neuron 1617 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: 7.6743. Min Range: -7.6743

Max Act: 7.6743. Min Act: -0.0000

Data Index: 1225050 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.1631. Min Act: -0.0000

Data Index: 1060300 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.7593. Min Act: -0.0000

Data Index: 1175729 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.1263. Min Act: -0.0000

Data Index: 675614 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.0355. Min Act: -0.0000

Data Index: 735875 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.1733. Min Act: -0.0000

Data Index: 425231 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.0003. Min Act: -0.0000

Data Index: 211708 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.9715. Min Act: -0.0000

Data Index: 1579343 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.6679. Min Act: -0.0000

Data Index: 549127 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.8559. Min Act: -0.0000

Data Index: 902266 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.0206. Min Act: -0.0000

Data Index: 846395 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.8255. Min Act: -0.0000

Data Index: 870547 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.7981. Min Act: -0.0000

Data Index: 1988278 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.9823. Min Act: -0.0000

Data Index: 323937 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.7690. Min Act: -0.0000

Data Index: 718358 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.9867. Min Act: -0.0000

Data Index: 589217 (The Pile)

Max Activating Token Index: 632

Text #16

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.1847. Min Act: -0.0000

Data Index: 898525 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.9422. Min Act: -0.0000

Data Index: 1433264 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 7.6743. Min Range: -7.6743

Max Act: 6.7607. Min Act: -0.0000

Data Index: 565638 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 7.6743. Min Range: -7.6743

Max Act: 7.0708. Min Act: -0.0000

Data Index: 1397912 (The Pile)

Max Activating Token Index: 617