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

Dataset: The Pile

Neuron 3082 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: 0.8836. Min Range: -0.8836

Max Act: 0.8155. Min Act: -0.0000

Data Index: 451325 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0000

Data Index: 88772 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8354. Min Act: -0.0000

Data Index: 386049 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7479. Min Act: -0.0000

Data Index: 865058 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7715. Min Act: -0.0000

Data Index: 447760 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1996738 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1781302 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1309906 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1539523 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1108515 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6992. Min Act: -0.0000

Data Index: 520561 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1951871 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1321422 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7457. Min Act: -0.0000

Data Index: 590805 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1595782 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1908640 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6346. Min Act: -0.0000

Data Index: 348132 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1231496 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1126196 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1788010 (The Pile)

Max Activating Token Index: 46