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

Dataset: The Pile

Neuron 1824 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: 0.7815. Min Range: -0.7815

Max Act: 0.7526. Min Act: -0.0000

Data Index: 567714 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7815. Min Act: -0.0000

Data Index: 672576 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1775379 (The Pile)

Max Activating Token Index: 237

Text #3

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1568817 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1033147 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1792466 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1106517 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1080188 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6726. Min Act: -0.0000

Data Index: 607177 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1580131 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1897083 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1751139 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6210. Min Act: -0.0000

Data Index: 206091 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6389. Min Act: -0.0000

Data Index: 636406 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1051906 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1810904 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5766. Min Act: -0.0000

Data Index: 296789 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5725. Min Act: -0.0000

Data Index: 913948 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5898. Min Act: -0.0000

Data Index: 257547 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1604833 (The Pile)

Max Activating Token Index: 68