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

Dataset: The Pile

Neuron 4721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1341181 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1164862 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.2557. Min Act: -0.0000

Data Index: 696702 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1800373 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.2627. Min Act: -0.0000

Data Index: 76454 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1469002 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0764. Min Act: -0.0000

Data Index: 720844 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.1911. Min Act: -0.0000

Data Index: 883883 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1069092 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0194. Min Act: -0.0000

Data Index: 897635 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0081. Min Act: -0.0000

Data Index: 244867 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0349. Min Act: -0.0000

Data Index: 563801 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0424. Min Act: -0.0000

Data Index: 329855 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 1.5126. Min Range: -1.5126

Max Act: 0.9977. Min Act: -0.0000

Data Index: 114398 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 1.5126. Min Range: -1.5126

Max Act: 0.9601. Min Act: -0.0000

Data Index: 647002 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 1.5126. Min Range: -1.5126

Max Act: 0.9856. Min Act: -0.0000

Data Index: 899800 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 1.5126. Min Range: -1.5126

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1958307 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1130385 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 1.5126. Min Range: -1.5126

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1980569 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 1.5126. Min Range: -1.5126

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1615880 (The Pile)

Max Activating Token Index: 676