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

Dataset: The Pile

Neuron 1050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5932. Min Act: -0.0000

Data Index: 753565 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1358815 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1048583 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4592. Min Act: -0.0000

Data Index: 963303 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4698. Min Act: -0.0000

Data Index: 609717 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4348. Min Act: -0.0000

Data Index: 271576 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4124. Min Act: -0.0000

Data Index: 611430 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4210. Min Act: 0.0000

Data Index: 377601 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4265. Min Act: -0.0000

Data Index: 673173 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1905785 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1005213 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3889. Min Act: -0.0000

Data Index: 302148 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1413794 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3914. Min Act: -0.0000

Data Index: 867165 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1682662 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3802. Min Act: -0.0000

Data Index: 99954 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1807329 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3799. Min Act: -0.0000

Data Index: 533875 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3661. Min Act: 0.0000

Data Index: 1617572 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3898. Min Act: 0.0000

Data Index: 1770897 (The Pile)

Max Activating Token Index: 144