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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1781. Min Act: -0.0000

Data Index: 955433 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1600. Min Act: -0.0000

Data Index: 134352 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1682. Min Act: -0.0000

Data Index: 286011 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1512. Min Act: -0.0000

Data Index: 480016 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1440. Min Act: -0.0000

Data Index: 932224 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1247750 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1415. Min Act: -0.0000

Data Index: 66670 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1394. Min Act: -0.0000

Data Index: 876223 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1438. Min Act: -0.0000

Data Index: 883918 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1320. Min Act: -0.0000

Data Index: 508905 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1367. Min Act: -0.0000

Data Index: 386781 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1358. Min Act: -0.0000

Data Index: 468949 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1328. Min Act: -0.0000

Data Index: 683333 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1286. Min Act: -0.0000

Data Index: 297155 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1203. Min Act: -0.0000

Data Index: 121359 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1390756 (Python Code)

Max Activating Token Index: 560

Text #16

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1280584 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1011970 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1133. Min Act: -0.0000

Data Index: 735752 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1781. Min Range: -0.1781

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1645552 (Python Code)

Max Activating Token Index: 489