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

Dataset: The Pile

Neuron 4153 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.9630. Min Act: -0.0000

Data Index: 270341 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 1.0250. Min Range: -1.0250

Max Act: 1.0250. Min Act: -0.0000

Data Index: 719461 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1018967 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1045427 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.8581. Min Act: -0.0000

Data Index: 627377 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7504. Min Act: -0.0000

Data Index: 540254 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7675. Min Act: -0.0000

Data Index: 637139 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7922. Min Act: 0.0000

Data Index: 77768 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7750. Min Act: -0.0000

Data Index: 789738 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7327. Min Act: -0.0000

Data Index: 251941 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1599457 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7102. Min Act: -0.0000

Data Index: 501888 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7430. Min Act: -0.0000

Data Index: 869995 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1044503 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6817. Min Act: -0.0000

Data Index: 15305 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7430. Min Act: 0.0000

Data Index: 109888 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6778. Min Act: -0.0000

Data Index: 364673 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1301765 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.6769. Min Act: -0.0000

Data Index: 681761 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 1.0250. Min Range: -1.0250

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1631992 (The Pile)

Max Activating Token Index: 116