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

Dataset: The Pile

Neuron 3618 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: 1.7707. Min Range: -1.7707

Max Act: 1.7660. Min Act: -0.0000

Data Index: 1347816 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.7707. Min Act: -0.0000

Data Index: 283794 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1323094 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1350697 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.6529. Min Act: -0.0000

Data Index: 870255 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1977341 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1761679 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5377. Min Act: -0.0000

Data Index: 1154720 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1673192 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5062. Min Act: -0.0000

Data Index: 406668 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1116993 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1670296 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1963711 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4171. Min Act: -0.0000

Data Index: 638941 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1115610 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1222959 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4333. Min Act: -0.0000

Data Index: 805208 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1761746 (The Pile)

Max Activating Token Index: 536

Text #18

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4001. Min Act: -0.0000

Data Index: 522781 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1587336 (The Pile)

Max Activating Token Index: 200