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

Dataset: The Pile

Neuron 1972 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: 0.2477. Min Range: -0.2477

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1811917 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1710. Min Act: -0.0000

Data Index: 793755 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1526. Min Act: -0.0000

Data Index: 409848 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1894221 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1019103 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1710746 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1387. Min Act: -0.0000

Data Index: 102426 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1390. Min Act: -0.0000

Data Index: 939133 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1321. Min Act: -0.0000

Data Index: 816072 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1278153 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1075918 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1422193 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1362. Min Act: -0.0000

Data Index: 321246 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1269. Min Act: -0.0000

Data Index: 862744 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1264. Min Act: -0.0000

Data Index: 243847 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1254. Min Act: -0.0000

Data Index: 894153 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1248. Min Act: -0.0000

Data Index: 434634 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1143601 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1246. Min Act: -0.0000

Data Index: 126814 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1976980 (The Pile)

Max Activating Token Index: 172