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

Dataset: The Pile

Neuron 2016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1247657 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8430. Min Act: -0.0000

Data Index: 497013 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7830. Min Act: -0.0000

Data Index: 724990 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1755600 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6696. Min Act: -0.0000

Data Index: 785475 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6785. Min Act: -0.0000

Data Index: 961065 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1090423 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1348657 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1063672 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7127. Min Act: -0.0000

Data Index: 747210 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6820. Min Act: -0.0000

Data Index: 371278 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1175346 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1337547 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6786. Min Act: -0.0000

Data Index: 33391 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6053. Min Act: -0.0000

Data Index: 124965 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1087342 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1144301 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.5970. Min Act: -0.0000

Data Index: 481471 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.7150. Min Act: -0.0000

Data Index: 134414 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.9094. Min Range: -0.9094

Max Act: 0.6166. Min Act: -0.0000

Data Index: 535410 (The Pile)

Max Activating Token Index: 730