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

Dataset: The Pile

Neuron 4585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1956509 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9730. Min Act: -0.0000

Data Index: 930549 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0716. Min Act: -0.0000

Data Index: 446287 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9403. Min Act: -0.0000

Data Index: 267991 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8363. Min Act: -0.0000

Data Index: 560645 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8590. Min Act: -0.0000

Data Index: 190251 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7845. Min Act: -0.0000

Data Index: 895617 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8423. Min Act: -0.0001

Data Index: 184760 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1409002 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1682702 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1812469 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1589846 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7910. Min Act: -0.0000

Data Index: 800727 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1843614 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1224144 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7213. Min Act: -0.0000

Data Index: 640180 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7328. Min Act: -0.0000

Data Index: 903551 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.6820. Min Act: -0.0000

Data Index: 627712 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1094927 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1922739 (The Pile)

Max Activating Token Index: 357