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

Dataset: The Pile

Neuron 3757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1745874 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1078863 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.1329. Min Act: -0.0000

Data Index: 552697 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.1008. Min Act: -0.0000

Data Index: 51758 (The Pile)

Max Activating Token Index: 295

Text #4

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0153. Min Act: -0.0000

Data Index: 75324 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0001. Min Act: -0.0000

Data Index: 110709 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1996546 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1197583 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9844. Min Act: -0.0000

Data Index: 981768 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1358522 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1436775 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9430. Min Act: -0.0000

Data Index: 473262 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9955. Min Act: -0.0000

Data Index: 56431 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9009. Min Act: -0.0000

Data Index: 383392 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1711276 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1323249 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9592. Min Act: -0.0000

Data Index: 679010 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9594. Min Act: -0.0000

Data Index: 465386 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8901. Min Act: -0.0000

Data Index: 472436 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8677. Min Act: -0.0000

Data Index: 968939 (The Pile)

Max Activating Token Index: 665