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

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

Neuron 2022 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1522981 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1572156 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1430537 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1554676 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1540560 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1422944 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1388609 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1490783 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1604641 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1495063 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1609720 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1599769 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1456505 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1432590 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1406518 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1436377 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1655387 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1387013 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1575590 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1410533 (Python Code)

Max Activating Token Index: 450