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

Dataset: The Pile

Neuron 4631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1623. Min Range: -5.1623

Max Act: 5.1623. Min Act: -0.0000

Data Index: 1679415 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.8063. Min Act: -0.0000

Data Index: 1026796 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.8516. Min Act: -0.0000

Data Index: 864028 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1674765 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.7138. Min Act: -0.0000

Data Index: 1989202 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1926346 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.5149. Min Act: -0.0000

Data Index: 249790 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1103570 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.2173. Min Act: -0.0000

Data Index: 1580905 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.4270. Min Act: -0.0000

Data Index: 968262 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.3361. Min Act: -0.0000

Data Index: 982071 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.3280. Min Act: -0.0000

Data Index: 34904 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.2045. Min Act: -0.0000

Data Index: 87084 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 5.1623. Min Range: -5.1623

Max Act: 1.9544. Min Act: -0.0000

Data Index: 1398268 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.5148. Min Act: -0.0000

Data Index: 1110717 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.0743. Min Act: -0.0000

Data Index: 302509 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1177717 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 5.1623. Min Range: -5.1623

Max Act: 1.9908. Min Act: -0.0000

Data Index: 1767129 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.0908. Min Act: -0.0000

Data Index: 649907 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 5.1623. Min Range: -5.1623

Max Act: 2.0488. Min Act: -0.0000

Data Index: 1492703 (The Pile)

Max Activating Token Index: 401