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

Dataset: The Pile

Neuron 1677 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: 0.7462. Min Range: -0.7462

Max Act: 0.7462. Min Act: -0.0000

Data Index: 262467 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1183592 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1647525 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1812642 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1926525 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5926. Min Act: -0.0000

Data Index: 273364 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6165. Min Act: -0.0000

Data Index: 228796 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1205371 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6190. Min Act: -0.0000

Data Index: 362007 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1501945 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5844. Min Act: -0.0000

Data Index: 453318 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1612790 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6104. Min Act: -0.0000

Data Index: 7883 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1887821 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1322080 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1326905 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1621022 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6144. Min Act: -0.0000

Data Index: 130832 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5570. Min Act: -0.0000

Data Index: 980615 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5557. Min Act: -0.0000

Data Index: 704442 (The Pile)

Max Activating Token Index: 535