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

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

Neuron 5678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2297. Min Act: -0.0000

Data Index: 934870 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0000

Data Index: 20916 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1898. Min Act: -0.0000

Data Index: 648816 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1276652 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1809. Min Act: 0.0000

Data Index: 816350 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1811. Min Act: 0.0000

Data Index: 829641 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1675. Min Act: -0.0000

Data Index: 357955 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1734. Min Act: -0.0000

Data Index: 383777 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1065565 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1692. Min Act: -0.0000

Data Index: 925655 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1593. Min Act: -0.0000

Data Index: 600545 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1325326 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1609144 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1127369 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1501. Min Act: 0.0000

Data Index: 571131 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1098286 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1511. Min Act: -0.0000

Data Index: 520597 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1027845 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1567. Min Act: -0.0000

Data Index: 117691 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1006768 (C4 (Web Text))

Max Activating Token Index: 370