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

Dataset: The Pile

Neuron 4418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1742. Min Range: -5.1742

Max Act: 5.1742. Min Act: -0.0000

Data Index: 934541 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.7038. Min Act: -0.0000

Data Index: 1919243 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.1893. Min Act: -0.0000

Data Index: 264952 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.1604. Min Act: -0.0000

Data Index: 1996609 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.5208. Min Act: -0.0000

Data Index: 49429 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.1148. Min Act: -0.0000

Data Index: 1083253 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.2827. Min Act: -0.0000

Data Index: 40677 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.2263. Min Act: -0.0000

Data Index: 92675 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.9151. Min Act: -0.0000

Data Index: 1388640 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.9106. Min Act: -0.0000

Data Index: 1136352 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.7646. Min Act: -0.0000

Data Index: 1665888 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.8743. Min Act: -0.0000

Data Index: 1873146 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.0113. Min Act: -0.0000

Data Index: 1066462 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 5.1742. Min Range: -5.1742

Max Act: 4.0074. Min Act: -0.0000

Data Index: 1707150 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.6530. Min Act: -0.0000

Data Index: 62296 (The Pile)

Max Activating Token Index: 781

Text #15

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.6308. Min Act: -0.0000

Data Index: 1926287 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.6161. Min Act: -0.0000

Data Index: 299019 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.7384. Min Act: -0.0000

Data Index: 1896235 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.5804. Min Act: -0.0000

Data Index: 103230 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 5.1742. Min Range: -5.1742

Max Act: 3.7334. Min Act: -0.0000

Data Index: 1564591 (The Pile)

Max Activating Token Index: 62