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

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

Neuron 1239 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0005

Data Index: 1113185 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1658. Min Act: -0.0005

Data Index: 378526 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1449. Min Act: -0.0005

Data Index: 792641 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1452. Min Act: -0.0005

Data Index: 706935 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1497. Min Act: -0.0005

Data Index: 49825 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1442. Min Act: -0.0005

Data Index: 78445 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1409. Min Act: -0.0005

Data Index: 800115 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1387. Min Act: -0.0005

Data Index: 1055396 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1446. Min Act: -0.0005

Data Index: 805971 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1306. Min Act: -0.0005

Data Index: 545852 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1324. Min Act: -0.0005

Data Index: 630889 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1274. Min Act: -0.0005

Data Index: 1023746 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1323. Min Act: -0.0005

Data Index: 314461 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1217. Min Act: -0.0005

Data Index: 1349165 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1248. Min Act: -0.0005

Data Index: 108829 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1318. Min Act: -0.0005

Data Index: 311903 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1281. Min Act: -0.0005

Data Index: 368269 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1226. Min Act: -0.0005

Data Index: 1170000 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1308. Min Act: -0.0005

Data Index: 1345422 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1214. Min Act: -0.0005

Data Index: 208948 (C4 (Web Text))

Max Activating Token Index: 524