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

Dataset: The Pile

Neuron 4216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.2590. Min Act: 0.0001

Data Index: 1676922 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.1102. Min Act: -0.0000

Data Index: 543024 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.2207. Min Act: -0.0000

Data Index: 80930 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.2676. Min Act: -0.0000

Data Index: 670171 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1499138 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0644. Min Act: -0.0000

Data Index: 648336 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1514095 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.1313. Min Act: -0.0000

Data Index: 268036 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1695448 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0969. Min Act: 0.0000

Data Index: 293524 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1443910 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0606. Min Act: 0.0000

Data Index: 280409 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0348. Min Act: -0.0000

Data Index: 471896 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1717248 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1388418 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0098. Min Act: 0.0000

Data Index: 1190160 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 1.2676. Min Range: -1.2676

Max Act: 0.9360. Min Act: -0.0000

Data Index: 225240 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 1.2676. Min Range: -1.2676

Max Act: 0.9367. Min Act: -0.0000

Data Index: 303652 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.2676. Min Range: -1.2676

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1566267 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.2676. Min Range: -1.2676

Max Act: 1.0476. Min Act: -0.0000

Data Index: 231058 (The Pile)

Max Activating Token Index: 196