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

Dataset: The Pile

Neuron 4946 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1792902 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1621698 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5474. Min Act: -0.0000

Data Index: 752954 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5392. Min Act: -0.0000

Data Index: 403805 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5957. Min Act: -0.0000

Data Index: 862255 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1969758 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5074. Min Act: -0.0000

Data Index: 251661 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5126. Min Act: -0.0000

Data Index: 192540 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1906064 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1087566 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4806. Min Act: -0.0000

Data Index: 42010 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1386311 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1427839 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5037. Min Act: -0.0000

Data Index: 982680 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1941754 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4745. Min Act: -0.0000

Data Index: 61519 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1108597 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1700600 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4725. Min Act: -0.0000

Data Index: 680126 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1805452 (The Pile)

Max Activating Token Index: 649