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

Dataset: The Pile

Neuron 4368 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: 1.5813. Min Range: -1.5813

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1358922 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1164188 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1276528 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2542. Min Act: -0.0000

Data Index: 748977 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1260722 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2303. Min Act: -0.0000

Data Index: 343083 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.3047. Min Act: -0.0000

Data Index: 655091 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1315993 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1434. Min Act: -0.0000

Data Index: 865657 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.5813. Min Range: -1.5813

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1295018 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1340185 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1419715 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1300507 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1434090 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0359. Min Act: -0.0000

Data Index: 326592 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1624. Min Act: -0.0000

Data Index: 202955 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1675205 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1940465 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1010096 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1230. Min Act: -0.0000

Data Index: 364737 (The Pile)

Max Activating Token Index: 339