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

Dataset: The Pile

Neuron 3182 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: 1.2770. Min Range: -1.2770

Max Act: 1.2770. Min Act: -0.0000

Data Index: 621434 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1720. Min Act: -0.0000

Data Index: 706484 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1477610 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1087594 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.2515. Min Act: -0.0000

Data Index: 50490 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1765. Min Act: -0.0000

Data Index: 743445 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1777601 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1921637 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1734188 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1135709 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1290. Min Act: -0.0000

Data Index: 683675 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1239. Min Act: -0.0000

Data Index: 67382 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1352. Min Act: -0.0000

Data Index: 918517 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.0516. Min Act: -0.0000

Data Index: 716171 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1073. Min Act: -0.0000

Data Index: 907586 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1045056 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.1175. Min Act: -0.0000

Data Index: 694715 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1636862 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1168034 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.2770. Min Range: -1.2770

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1581698 (The Pile)

Max Activating Token Index: 325