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

Dataset: The Pile

Neuron 4568 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: 0.7430. Min Range: -0.7430

Max Act: 0.7430. Min Act: -0.0000

Data Index: 304213 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5953. Min Act: -0.0000

Data Index: 714063 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6892. Min Act: -0.0000

Data Index: 136913 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1991603 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6864. Min Act: -0.0000

Data Index: 611055 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.7031. Min Act: -0.0000

Data Index: 401682 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6520. Min Act: -0.0000

Data Index: 647144 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5172. Min Act: -0.0000

Data Index: 422987 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1696269 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6363. Min Act: -0.0000

Data Index: 400946 (The Pile)

Max Activating Token Index: 407

Text #10

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1689809 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1657674 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1596259 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1908777 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6266. Min Act: -0.0000

Data Index: 934603 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1204012 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6162. Min Act: -0.0000

Data Index: 189557 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1066143 (The Pile)

Max Activating Token Index: 218

Text #18

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1030225 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.7430. Min Range: -0.7430

Max Act: 0.5646. Min Act: -0.0000

Data Index: 558788 (The Pile)

Max Activating Token Index: 181