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

Dataset: The Pile

Neuron 1160 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: 0.6019. Min Range: -0.6019

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1597475 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5430. Min Act: -0.0000

Data Index: 766596 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1592385 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5072. Min Act: -0.0000

Data Index: 452930 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5046. Min Act: -0.0000

Data Index: 802385 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1037369 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4844. Min Act: -0.0000

Data Index: 823632 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1577046 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1356598 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1453370 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5104. Min Act: -0.0000

Data Index: 588412 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1362268 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1350863 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4066. Min Act: -0.0000

Data Index: 845692 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4141. Min Act: -0.0000

Data Index: 211043 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1741246 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4228. Min Act: -0.0000

Data Index: 135327 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1771960 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1693206 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3910. Min Act: -0.0000

Data Index: 64438 (The Pile)

Max Activating Token Index: 878