Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 927 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1732. Min Act: -0.0002

Data Index: 1575800 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1554069 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1482632 (Python Code)

Max Activating Token Index: 477

Text #3

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1629081 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1546416 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1247. Min Act: -0.0002

Data Index: 1536685 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1407637 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1437220 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1639158 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1378948 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1380557 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1444739 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1533206 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1633545 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1419713 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1477780 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1374931 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1632660 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1566973 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 0.1732. Min Range: -0.1732

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1507837 (Python Code)

Max Activating Token Index: 527