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

Dataset: The Pile

Neuron 3203 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1183986 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1707. Min Act: -0.0000

Data Index: 642975 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1786519 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1294. Min Act: -0.0000

Data Index: 920846 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1341. Min Act: -0.0000

Data Index: 952027 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1416659 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1719144 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1711640 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1339. Min Act: -0.0000

Data Index: 624847 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1544988 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1399. Min Act: -0.0000

Data Index: 76059 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1232721 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1300. Min Act: -0.0000

Data Index: 950433 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1306. Min Act: -0.0000

Data Index: 132259 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1183722 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1200055 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1345106 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1244. Min Act: -0.0000

Data Index: 425841 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1911362 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1831293 (The Pile)

Max Activating Token Index: 89