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

Dataset: The Pile

Neuron 2474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.4658. Min Act: -0.0000

Data Index: 460731 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.3176. Min Act: -0.0000

Data Index: 448373 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1753440 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1682089 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0843. Min Act: -0.0000

Data Index: 498086 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1194. Min Act: -0.0000

Data Index: 409965 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0943. Min Act: -0.0000

Data Index: 17579 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1482371 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1010. Min Act: -0.0000

Data Index: 167077 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9686. Min Act: -0.0000

Data Index: 497768 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0203. Min Act: -0.0000

Data Index: 705599 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9603. Min Act: -0.0000

Data Index: 901782 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1562244 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1287645 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1643040 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1094243 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1405845 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.8792. Min Act: -0.0000

Data Index: 305083 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.8783. Min Act: -0.0000

Data Index: 847290 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1216075 (The Pile)

Max Activating Token Index: 58