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

Dataset: The Pile

Neuron 712 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: 3.9722. Min Range: -3.9722

Max Act: 3.9722. Min Act: -0.0000

Data Index: 239094 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.9645. Min Act: -0.0000

Data Index: 1927808 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.7050. Min Act: -0.0000

Data Index: 1174192 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.5843. Min Act: -0.0000

Data Index: 217589 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.6019. Min Act: -0.0000

Data Index: 450116 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.5644. Min Act: -0.0000

Data Index: 1090083 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4913. Min Act: -0.0000

Data Index: 528327 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4821. Min Act: -0.0000

Data Index: 1982035 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4693. Min Act: -0.0000

Data Index: 1590568 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4712. Min Act: -0.0000

Data Index: 542429 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.2973. Min Act: -0.0000

Data Index: 796822 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4452. Min Act: -0.0000

Data Index: 1718116 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4072. Min Act: -0.0000

Data Index: 1186634 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.4110. Min Act: -0.0000

Data Index: 1707528 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.2457. Min Act: -0.0000

Data Index: 1348377 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.3690. Min Act: -0.0000

Data Index: 1027348 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.5222. Min Act: -0.0000

Data Index: 775063 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.3415. Min Act: -0.0000

Data Index: 1016460 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.2194. Min Act: -0.0000

Data Index: 1929397 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 3.9722. Min Range: -3.9722

Max Act: 3.3416. Min Act: -0.0000

Data Index: 1861278 (The Pile)

Max Activating Token Index: 30