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

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

Neuron 2428 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: 0.2109. Min Range: -0.2109

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1519734 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1586033 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1991. Min Act: -0.0000

Data Index: 708713 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1866. Min Act: -0.0000

Data Index: 937619 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1066491 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1374312 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1438213 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1565841 (Python Code)

Max Activating Token Index: 663

Text #9

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1527879 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1372449 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1606. Min Act: -0.0000

Data Index: 502595 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1594329 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1431094 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1369516 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1305849 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1408. Min Act: -0.0000

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1377225 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1576814 (Python Code)

Max Activating Token Index: 257

Text #19

Max Range: 0.2109. Min Range: -0.2109

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1378476 (Python Code)

Max Activating Token Index: 675