Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 447 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1472694 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1389390 (Python Code)

Max Activating Token Index: 435

Text #2

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1441538 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1619023 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1651754 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1433485 (Python Code)

Max Activating Token Index: 426

Text #6

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1560375 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1621812 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1571338 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1495339 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1438701 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1589722 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1449332 (Python Code)

Max Activating Token Index: 393

Text #13

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1480762 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1552248 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1480354 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1484553 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1649750 (Python Code)

Max Activating Token Index: 743

Text #18

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1566825 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.1907. Min Range: -0.1907

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1485372 (Python Code)

Max Activating Token Index: 248