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

Dataset: The Pile

Neuron 4864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1535105 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1581036 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1558406 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1598448 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6219. Min Act: -0.0000

Data Index: 872779 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5699. Min Act: -0.0000

Data Index: 761092 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1886568 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5895. Min Act: -0.0000

Data Index: 637405 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1190973 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5941. Min Act: -0.0000

Data Index: 330001 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5764. Min Act: -0.0000

Data Index: 995169 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1087755 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6101. Min Act: -0.0000

Data Index: 924776 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1976739 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5777. Min Act: -0.0000

Data Index: 928866 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5483. Min Act: -0.0000

Data Index: 502833 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1345197 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1609890 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1449405 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1207755 (The Pile)

Max Activating Token Index: 637