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

Dataset: The Pile

Neuron 3952 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: 0.7200. Min Range: -0.7200

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1757422 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6500. Min Act: -0.0000

Data Index: 585946 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6692. Min Act: -0.0000

Data Index: 496973 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6583. Min Act: -0.0000

Data Index: 977773 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1300131 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6608. Min Act: -0.0000

Data Index: 67200 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1474140 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1374154 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1591107 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6924. Min Act: -0.0000

Data Index: 146741 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6317. Min Act: -0.0000

Data Index: 653733 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6375. Min Act: -0.0000

Data Index: 744665 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6122. Min Act: -0.0000

Data Index: 304946 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5914. Min Act: -0.0000

Data Index: 506184 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1299162 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6114. Min Act: -0.0000

Data Index: 195817 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5714. Min Act: -0.0000

Data Index: 213074 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1695086 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6367. Min Act: -0.0000

Data Index: 356896 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.7200. Min Range: -0.7200

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1501657 (The Pile)

Max Activating Token Index: 804