Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9530. Min Act: -0.0000

Data Index: 1435388 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6187. Min Act: -0.0000

Data Index: 326675 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.4643. Min Act: -0.0000

Data Index: 319585 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1636243 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1572399 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2605. Min Act: -0.0000

Data Index: 346152 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1702571 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1628219 (The Pile)

Max Activating Token Index: 12

Text #8

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1551970 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1590784 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1993866 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2252. Min Act: -0.0000

Data Index: 97684 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1917117 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1801. Min Act: -0.0000

Data Index: 18626 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1806. Min Act: -0.0000

Data Index: 851534 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1673. Min Act: 0.0000

Data Index: 1382524 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1232246 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1046243 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.1833. Min Act: -0.0000

Data Index: 615279 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1691068 (The Pile)

Max Activating Token Index: 812