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

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

Neuron 4202 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1469571 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1603890 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1545400 (Python Code)

Max Activating Token Index: 361

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1427237 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1572906 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1393. Min Act: -0.0001

Data Index: 162547 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1494663 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1484. Min Act: -0.0001

Data Index: 968707 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1524776 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1423. Min Act: -0.0001

Data Index: 574622 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1407. Min Act: -0.0001

Data Index: 225449 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1480635 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1627025 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1634872 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1460215 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1495987 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1529484 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1570370 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1285773 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1638586 (Python Code)

Max Activating Token Index: 308