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

Dataset: The Pile

Neuron 2794 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: 1.7767. Min Range: -1.7767

Max Act: 1.7767. Min Act: -0.0000

Data Index: 504619 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.3671. Min Act: -0.0000

Data Index: 627040 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1518744 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1470794 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1711940 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1711202 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1740502 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1276700 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8865. Min Act: -0.0000

Data Index: 152463 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1085434 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8697. Min Act: -0.0000

Data Index: 210478 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8779. Min Act: -0.0000

Data Index: 300931 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.9210. Min Act: -0.0000

Data Index: 668388 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8684. Min Act: -0.0000

Data Index: 437905 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1358356 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8461. Min Act: -0.0000

Data Index: 168731 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.7915. Min Act: -0.0000

Data Index: 605629 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1340730 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8812. Min Act: 0.0000

Data Index: 1626333 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 1.7767. Min Range: -1.7767

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1635412 (The Pile)

Max Activating Token Index: 631