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

Dataset: The Pile

Neuron 4695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.8251. Min Act: -0.0000

Data Index: 1903277 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1620909 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7297. Min Act: -0.0000

Data Index: 874412 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7350. Min Act: -0.0000

Data Index: 1906532 (The Pile)

Max Activating Token Index: 600

Text #4

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7260. Min Act: -0.0000

Data Index: 814956 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1350425 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7005. Min Act: -0.0000

Data Index: 99050 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6194. Min Act: -0.0000

Data Index: 451294 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6955. Min Act: -0.0000

Data Index: 1473429 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1389195 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6626. Min Act: -0.0000

Data Index: 268243 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1849275 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6402. Min Act: -0.0000

Data Index: 1159617 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5564. Min Act: -0.0000

Data Index: 1952554 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6349. Min Act: -0.0000

Data Index: 1115868 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6398. Min Act: -0.0000

Data Index: 1371424 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7315. Min Act: -0.0000

Data Index: 183581 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.7274. Min Act: -0.0000

Data Index: 70581 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.5393. Min Act: -0.0000

Data Index: 807525 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 1.9211. Min Range: -1.9211

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1240905 (The Pile)

Max Activating Token Index: 800