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

Dataset: The Pile

Neuron 5019 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: 3.7678. Min Range: -3.7678

Max Act: 3.7678. Min Act: -0.0000

Data Index: 934124 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.7380. Min Act: -0.0000

Data Index: 654970 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.7291. Min Act: -0.0000

Data Index: 353285 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.5164. Min Act: -0.0000

Data Index: 1916490 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.4700. Min Act: -0.0000

Data Index: 1498106 (The Pile)

Max Activating Token Index: 454

Text #5

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.4858. Min Act: -0.0000

Data Index: 1858559 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.2961. Min Act: -0.0000

Data Index: 662276 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.2727. Min Act: -0.0000

Data Index: 360461 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.1947. Min Act: -0.0000

Data Index: 611720 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9943. Min Act: -0.0000

Data Index: 836689 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.1227. Min Act: -0.0000

Data Index: 1717995 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9905. Min Act: -0.0000

Data Index: 707801 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9616. Min Act: -0.0000

Data Index: 1020152 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.2210. Min Act: -0.0000

Data Index: 359128 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 3.7678. Min Range: -3.7678

Max Act: 3.0444. Min Act: -0.0000

Data Index: 595563 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9851. Min Act: -0.0000

Data Index: 567672 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9383. Min Act: -0.0000

Data Index: 886717 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9413. Min Act: -0.0000

Data Index: 752410 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.9176. Min Act: -0.0000

Data Index: 41764 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 3.7678. Min Range: -3.7678

Max Act: 2.7651. Min Act: -0.0000

Data Index: 1413666 (The Pile)

Max Activating Token Index: 646