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

Dataset: The Pile

Neuron 4003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1445471 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1986103 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1795030 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1160621 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0583. Min Act: 0.0000

Data Index: 399371 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0604. Min Act: 0.0000

Data Index: 108561 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0688. Min Act: -0.0000

Data Index: 421900 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0600. Min Act: -0.0000

Data Index: 500786 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0579. Min Act: -0.0000

Data Index: 151448 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0614. Min Act: -0.0000

Data Index: 633519 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1549505 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0586. Min Act: -0.0000

Data Index: 273363 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1715013 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0626. Min Act: -0.0000

Data Index: 852165 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0597. Min Act: -0.0000

Data Index: 915407 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1367126 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1660680 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1403810 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0594. Min Act: -0.0000

Data Index: 716813 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1567251 (The Pile)

Max Activating Token Index: 993