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

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

Neuron 5009 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1491670 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1741. Min Act: -0.0001

Data Index: 1439673 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1361859 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1527191 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1547. Min Act: -0.0001

Data Index: 1631081 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1457546 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1614844 (Python Code)

Max Activating Token Index: 795

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1434732 (Python Code)

Max Activating Token Index: 855

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1490352 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1608672 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1626643 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1020593 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1417828 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1599555 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1404893 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1625473 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1487986 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1361995 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1577081 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1649222 (Python Code)

Max Activating Token Index: 964