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

Dataset: The Pile

Neuron 3000 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: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1291026 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5996. Min Act: -0.0000

Data Index: 370349 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1458731 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6422. Min Act: -0.0000

Data Index: 970766 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1644902 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1455012 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5719. Min Act: -0.0000

Data Index: 491098 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5580. Min Act: -0.0000

Data Index: 247842 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5548. Min Act: -0.0000

Data Index: 936289 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1819630 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1247115 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5191. Min Act: -0.0000

Data Index: 420745 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1457466 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1833855 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1485727 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5311. Min Act: 0.0000

Data Index: 462342 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1511898 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5283. Min Act: -0.0000

Data Index: 198216 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1555505 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4883. Min Act: -0.0000

Data Index: 332483 (The Pile)

Max Activating Token Index: 32