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

Dataset: The Pile

Neuron 2719 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: 1.9882. Min Range: -1.9882

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1327296 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5435. Min Act: -0.0000

Data Index: 1074324 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1442841 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.2204. Min Act: -0.0000

Data Index: 518017 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.3099. Min Act: -0.0000

Data Index: 475887 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1804. Min Act: -0.0000

Data Index: 264704 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4511. Min Act: -0.0000

Data Index: 191144 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1317581 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1647769 (The Pile)

Max Activating Token Index: 211

Text #9

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1985634 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1536983 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1614845 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1637474 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1345566 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1979728 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1386716 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1218366 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0187. Min Act: -0.0000

Data Index: 508797 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 1.9882. Min Range: -1.9882

Max Act: 0.9956. Min Act: -0.0000

Data Index: 139640 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1699086 (The Pile)

Max Activating Token Index: 784