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

Dataset: The Pile

Neuron 4915 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: 1.4701. Min Range: -1.4701

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1298507 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.4701. Min Act: -0.0000

Data Index: 531740 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3807. Min Act: -0.0000

Data Index: 445403 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1116845 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1087709 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2469. Min Act: -0.0000

Data Index: 23445 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2246. Min Act: -0.0000

Data Index: 190684 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1811857 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1086. Min Act: -0.0000

Data Index: 60298 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1302. Min Act: -0.0000

Data Index: 736057 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1256394 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1297273 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2709. Min Act: -0.0000

Data Index: 220408 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1338138 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1596608 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.2807. Min Act: -0.0000

Data Index: 404729 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1513. Min Act: -0.0000

Data Index: 652856 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1439. Min Act: -0.0000

Data Index: 531049 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.0588. Min Act: -0.0000

Data Index: 664539 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.4701. Min Range: -1.4701

Max Act: 1.1891. Min Act: -0.0000

Data Index: 644273 (The Pile)

Max Activating Token Index: 522