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

Dataset: The Pile

Neuron 4723 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: 1.7450. Min Range: -1.7450

Max Act: 1.6399. Min Act: -0.0000

Data Index: 400598 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1586626 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6747. Min Act: -0.0000

Data Index: 1101765 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5586. Min Act: -0.0000

Data Index: 560600 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1211767 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7207. Min Act: -0.0000

Data Index: 759796 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6272. Min Act: -0.0000

Data Index: 750060 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1860339 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7450. Min Act: -0.0000

Data Index: 30934 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6923. Min Act: -0.0000

Data Index: 703935 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1890320 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6486. Min Act: -0.0000

Data Index: 504012 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5994. Min Act: -0.0000

Data Index: 352315 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1598330 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1628914 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5643. Min Act: -0.0000

Data Index: 720596 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1592486 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5811. Min Act: -0.0000

Data Index: 442185 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.6981. Min Act: -0.0000

Data Index: 229346 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.5578. Min Act: -0.0000

Data Index: 178086 (The Pile)

Max Activating Token Index: 440