Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1540939 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3446. Min Act: -0.0000

Data Index: 729380 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1067010 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1625724 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1741963 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1237614 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1365075 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8727. Min Act: -0.0000

Data Index: 722174 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8564. Min Act: -0.0000

Data Index: 124182 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8556. Min Act: -0.0000

Data Index: 436965 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7999. Min Act: -0.0000

Data Index: 620025 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1873982 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7898. Min Act: -0.0000

Data Index: 126432 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1807334 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1050479 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7403. Min Act: -0.0000

Data Index: 358949 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7538. Min Act: -0.0000

Data Index: 261270 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7362. Min Act: -0.0000

Data Index: 232786 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.6884. Min Act: -0.0000

Data Index: 642342 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1549416 (The Pile)

Max Activating Token Index: 492