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

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

Neuron 2904 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1109827 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2367. Min Act: 0.0000

Data Index: 183601 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2316. Min Act: 0.0000

Data Index: 1246351 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1137661 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1210806 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1952. Min Act: -0.0000

Data Index: 253645 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1359829 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1625161 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1741. Min Act: -0.0000

Data Index: 934533 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1205728 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1546. Min Act: -0.0000

Data Index: 948517 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1176647 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1562. Min Act: -0.0000

Data Index: 501501 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1525. Min Act: -0.0000

Data Index: 398249 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1401869 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1367425 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1610313 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1417419 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1382. Min Act: -0.0000

Data Index: 820109 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.3461. Min Range: -0.3461

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1649631 (Python Code)

Max Activating Token Index: 761