Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1453486 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1529973 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1549. Min Act: -0.0000

Data Index: 453795 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1627100 (Python Code)

Max Activating Token Index: 234

Text #4

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1018103 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1649980 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1490279 (Python Code)

Max Activating Token Index: 718

Text #7

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1654294 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1614540 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1593691 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1417351 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1537724 (Python Code)

Max Activating Token Index: 609

Text #12

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1549115 (Python Code)

Max Activating Token Index: 207

Text #13

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1595030 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1518283 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1641737 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1524643 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1618685 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1446225 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1479797 (Python Code)

Max Activating Token Index: 246