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

Dataset: The Pile

Neuron 92 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: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0000

Data Index: 598405 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1701607 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7637. Min Act: -0.0000

Data Index: 60829 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1201882 (The Pile)

Max Activating Token Index: 476

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7842. Min Act: -0.0000

Data Index: 120148 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1490952 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7077. Min Act: -0.0000

Data Index: 824662 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6762. Min Act: -0.0000

Data Index: 75280 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1930878 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1133441 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1868350 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6423. Min Act: -0.0000

Data Index: 43978 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1201366 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1364259 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6143. Min Act: -0.0000

Data Index: 489683 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1822131 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1441265 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5632. Min Act: -0.0000

Data Index: 237893 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5249. Min Act: -0.0000

Data Index: 349085 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5705. Min Act: -0.0000

Data Index: 15048 (The Pile)

Max Activating Token Index: 910