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

Dataset: The Pile

Neuron 4657 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: 5.5678. Min Range: -5.5678

Max Act: 5.5678. Min Act: -0.0000

Data Index: 1780326 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.0015. Min Act: -0.0000

Data Index: 127543 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.5159. Min Act: -0.0000

Data Index: 1819710 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.2535. Min Act: -0.0000

Data Index: 1989130 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.0687. Min Act: -0.0000

Data Index: 1415403 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.0877. Min Act: -0.0000

Data Index: 1164891 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.5455. Min Act: -0.0000

Data Index: 1851324 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.3658. Min Act: -0.0000

Data Index: 574243 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.9003. Min Act: -0.0000

Data Index: 1378635 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 5.5678. Min Range: -5.5678

Max Act: 4.1682. Min Act: -0.0000

Data Index: 1216358 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.8713. Min Act: -0.0000

Data Index: 1216697 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.7472. Min Act: -0.0000

Data Index: 358722 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.7509. Min Act: -0.0000

Data Index: 1577592 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.7260. Min Act: -0.0000

Data Index: 1912767 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.9212. Min Act: -0.0000

Data Index: 940238 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.5410. Min Act: -0.0000

Data Index: 1104729 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.5509. Min Act: -0.0000

Data Index: 548969 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.7044. Min Act: -0.0000

Data Index: 1932766 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.6942. Min Act: -0.0000

Data Index: 1183165 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 5.5678. Min Range: -5.5678

Max Act: 3.4530. Min Act: -0.0000

Data Index: 461790 (The Pile)

Max Activating Token Index: 745