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

Dataset: The Pile

Neuron 800 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: 1.1438. Min Range: -1.1438

Max Act: 1.0885. Min Act: -0.0000

Data Index: 889004 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 1.1438. Min Range: -1.1438

Max Act: 1.1438. Min Act: -0.0000

Data Index: 928661 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.9926. Min Act: -0.0000

Data Index: 621912 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8959. Min Act: -0.0000

Data Index: 751541 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1208017 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1688483 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.9511. Min Act: -0.0000

Data Index: 74475 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8619. Min Act: -0.0000

Data Index: 581677 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1715280 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8690. Min Act: -0.0000

Data Index: 993483 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1673826 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1353155 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7823. Min Act: -0.0000

Data Index: 910674 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8066. Min Act: -0.0000

Data Index: 314122 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.9256. Min Act: -0.0000

Data Index: 752838 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7968. Min Act: -0.0000

Data Index: 41136 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7760. Min Act: -0.0000

Data Index: 129625 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8133. Min Act: -0.0000

Data Index: 390846 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1724923 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 1.1438. Min Range: -1.1438

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1784829 (The Pile)

Max Activating Token Index: 302