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

Dataset: The Pile

Neuron 1688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.1895. Min Act: -0.0000

Data Index: 632962 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.3511. Min Act: -0.0000

Data Index: 792598 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.2272. Min Act: -0.0000

Data Index: 20378 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.2064. Min Act: -0.0000

Data Index: 870527 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0340. Min Act: -0.0000

Data Index: 458792 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1605840 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0969. Min Act: -0.0000

Data Index: 588303 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1670516 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0031. Min Act: -0.0000

Data Index: 727149 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9903. Min Act: -0.0000

Data Index: 230252 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1375179 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9484. Min Act: -0.0000

Data Index: 434950 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1651290 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1050687 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1848886 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9182. Min Act: -0.0000

Data Index: 143664 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 1.3511. Min Range: -1.3511

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1961650 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.8885. Min Act: -0.0000

Data Index: 474469 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9717. Min Act: -0.0000

Data Index: 696621 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 1.3511. Min Range: -1.3511

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1871394 (The Pile)

Max Activating Token Index: 623