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

Dataset: The Pile

Neuron 125 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: 0.7508. Min Range: -0.7508

Max Act: 0.7508. Min Act: -0.0000

Data Index: 472959 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1880729 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1932160 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1742658 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4791. Min Act: -0.0000

Data Index: 450078 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5558. Min Act: -0.0000

Data Index: 337625 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5273. Min Act: -0.0000

Data Index: 345736 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1467004 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5190. Min Act: -0.0000

Data Index: 315414 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1625891 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4502. Min Act: -0.0000

Data Index: 617800 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1818491 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4165. Min Act: 0.0000

Data Index: 1573650 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1303192 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.3988. Min Act: 0.0000

Data Index: 1973592 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.3723. Min Act: -0.0000

Data Index: 554856 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1643865 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.3972. Min Act: -0.0000

Data Index: 964180 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4268. Min Act: -0.0000

Data Index: 529382 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.3698. Min Act: 0.0000

Data Index: 1412858 (The Pile)

Max Activating Token Index: 702