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

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

Neuron 1633 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: 0.1736. Min Range: -0.1736

Max Act: 0.1736. Min Act: -0.0002

Data Index: 139543 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1687. Min Act: -0.0001

Data Index: 400973 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1605. Min Act: -0.0002

Data Index: 1182504 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1532. Min Act: -0.0002

Data Index: 985125 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1447. Min Act: -0.0002

Data Index: 262159 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1488. Min Act: -0.0002

Data Index: 828206 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1105868 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1417. Min Act: -0.0002

Data Index: 519596 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1399. Min Act: -0.0002

Data Index: 381785 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1338. Min Act: -0.0002

Data Index: 71713 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1370. Min Act: -0.0002

Data Index: 561169 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1259327 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1287. Min Act: -0.0001

Data Index: 518437 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1341. Min Act: -0.0002

Data Index: 20943 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1336. Min Act: -0.0002

Data Index: 975300 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1329. Min Act: -0.0002

Data Index: 1000619 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1319. Min Act: -0.0002

Data Index: 585338 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1095887 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1299. Min Act: -0.0002

Data Index: 14031 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1296. Min Act: -0.0002

Data Index: 945403 (C4 (Web Text))

Max Activating Token Index: 304