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

Dataset: The Pile

Neuron 3491 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: 0.3588. Min Range: -0.3588

Max Act: 0.3588. Min Act: -0.0000

Data Index: 939947 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3046. Min Act: -0.0000

Data Index: 788305 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.3131. Min Act: -0.0000

Data Index: 693604 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2694. Min Act: -0.0000

Data Index: 680535 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2521. Min Act: -0.0000

Data Index: 189330 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1741167 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1853336 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2149. Min Act: -0.0000

Data Index: 734069 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1497331 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1278543 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1837523 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2054. Min Act: -0.0000

Data Index: 465284 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1786809 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1965. Min Act: -0.0000

Data Index: 189949 (The Pile)

Max Activating Token Index: 99

Text #14

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1645167 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1744048 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1981. Min Act: -0.0000

Data Index: 547762 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1609647 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1862. Min Act: -0.0000

Data Index: 839469 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.3588. Min Range: -0.3588

Max Act: 0.1693. Min Act: -0.0000

Data Index: 916166 (The Pile)

Max Activating Token Index: 531