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

Dataset: The Pile

Neuron 73 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: 1.4805. Min Range: -1.4805

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1633905 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 1.4805. Min Range: -1.4805

Max Act: 1.3568. Min Act: -0.0000

Data Index: 770313 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 1.4805. Min Range: -1.4805

Max Act: 1.1039. Min Act: -0.0000

Data Index: 259610 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.9765. Min Act: -0.0000

Data Index: 686950 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1099105 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1994594 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.9177. Min Act: -0.0000

Data Index: 843787 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1287685 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.9638. Min Act: -0.0000

Data Index: 124395 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8828. Min Act: -0.0000

Data Index: 179220 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1994209 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1620705 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1463075 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8858. Min Act: -0.0000

Data Index: 622333 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.9201. Min Act: -0.0000

Data Index: 19703 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1689339 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1076809 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8703. Min Act: -0.0000

Data Index: 606406 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1254493 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 1.4805. Min Range: -1.4805

Max Act: 0.8367. Min Act: -0.0000

Data Index: 464401 (The Pile)

Max Activating Token Index: 13