Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3127 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1378037 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1654941 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1784. Min Act: -0.0001

Data Index: 1633549 (Python Code)

Max Activating Token Index: 904

Text #3

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1593490 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1633067 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1420412 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1450140 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1595339 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1616159 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1544230 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1585699 (Python Code)

Max Activating Token Index: 948

Text #11

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1442719 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1383384 (Python Code)

Max Activating Token Index: 66

Text #13

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1531597 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1417329 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1654221 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1420169 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1574630 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1582532 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 0.3325. Min Range: -0.3325

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1434554 (Python Code)

Max Activating Token Index: 389