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

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

Neuron 2043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1514263 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1371350 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1434521 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1508728 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1567003 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1479524 (Python Code)

Max Activating Token Index: 639

Text #7

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1520522 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1578497 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1650374 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1384802 (Python Code)

Max Activating Token Index: 505

Text #11

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1610089 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1497110 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1475312 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1562436 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1459440 (Python Code)

Max Activating Token Index: 591

Text #16

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1527857 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1620017 (Python Code)

Max Activating Token Index: 878

Text #18

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1443671 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1428429 (Python Code)

Max Activating Token Index: 238