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

Dataset: The Pile

Neuron 2065 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: 0.9360. Min Range: -0.9360

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1633798 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1634820 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1190983 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1781342 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1010261 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1353549 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6960. Min Act: -0.0000

Data Index: 512159 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1641051 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1330209 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6553. Min Act: -0.0000

Data Index: 900656 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.5926. Min Act: -0.0000

Data Index: 987995 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1377447 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6439. Min Act: -0.0000

Data Index: 936557 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1410353 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6383. Min Act: -0.0000

Data Index: 793340 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.5929. Min Act: -0.0000

Data Index: 438062 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6474. Min Act: -0.0000

Data Index: 752221 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1726170 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1698038 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6666. Min Act: -0.0000

Data Index: 762467 (The Pile)

Max Activating Token Index: 28