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

Dataset: The Pile

Neuron 2470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1029084 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1123831 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1099514 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1660471 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1377253 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7783. Min Act: -0.0000

Data Index: 610454 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1221675 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1807890 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7791. Min Act: -0.0000

Data Index: 932285 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7809. Min Act: -0.0000

Data Index: 35415 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1897500 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7717. Min Act: -0.0000

Data Index: 672411 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1487129 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1686745 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1865984 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1700489 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1063586 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1990824 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7077. Min Act: -0.0000

Data Index: 166721 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7195. Min Act: -0.0000

Data Index: 819794 (The Pile)

Max Activating Token Index: 186