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

Dataset: The Pile

Neuron 2259 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.7209. Min Act: -0.0000

Data Index: 17665 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 3.1021. Min Range: -3.1021

Max Act: 3.1021. Min Act: -0.0000

Data Index: 1644418 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.7630. Min Act: -0.0000

Data Index: 1528252 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.5576. Min Act: -0.0000

Data Index: 492278 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.7988. Min Act: -0.0000

Data Index: 237853 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.4080. Min Act: -0.0000

Data Index: 1569819 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2705. Min Act: -0.0000

Data Index: 319009 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.4283. Min Act: -0.0000

Data Index: 1304550 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1091870 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.3972. Min Act: -0.0000

Data Index: 621475 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.3833. Min Act: -0.0000

Data Index: 1368406 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2083. Min Act: -0.0000

Data Index: 1154330 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.4442. Min Act: -0.0000

Data Index: 1449463 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1162151 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.3075. Min Act: -0.0000

Data Index: 1854432 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2959. Min Act: -0.0000

Data Index: 1821206 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.4111. Min Act: -0.0000

Data Index: 182137 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2453. Min Act: -0.0000

Data Index: 529450 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.2461. Min Act: -0.0000

Data Index: 1166947 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 3.1021. Min Range: -3.1021

Max Act: 2.0527. Min Act: -0.0000

Data Index: 246173 (The Pile)

Max Activating Token Index: 954