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

Dataset: The Pile

Neuron 2321 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: 1.1422. Min Range: -1.1422

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1568694 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1035103 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1960361 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0648. Min Act: -0.0000

Data Index: 722961 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1900007 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9811. Min Act: -0.0000

Data Index: 887938 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1568879 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 1.1422. Min Range: -1.1422

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1714719 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1647103 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9065. Min Act: -0.0000

Data Index: 464416 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8861. Min Act: -0.0000

Data Index: 701097 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9208. Min Act: -0.0000

Data Index: 148895 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1765936 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8892. Min Act: -0.0000

Data Index: 141183 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9145. Min Act: -0.0000

Data Index: 474300 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.9010. Min Act: -0.0000

Data Index: 770858 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1168004 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1341123 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1161079 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.1422. Min Range: -1.1422

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1664976 (The Pile)

Max Activating Token Index: 204