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

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

Neuron 1344 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.3895. Min Act: -0.0001

Data Index: 1589306 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1447791 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.3972. Min Act: -0.0001

Data Index: 1627256 (Python Code)

Max Activating Token Index: 649

Text #3

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1458500 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1385747 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1566817 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2708. Min Act: -0.0001

Data Index: 1645110 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1631760 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1372593 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1485069 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1608837 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1985. Min Act: -0.0001

Data Index: 1374451 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1433768 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1639. Min Act: -0.0001

Data Index: 1654887 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1372308 (Python Code)

Max Activating Token Index: 223

Text #15

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.0547. Min Act: -0.0001

Data Index: 1609870 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1552484 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.0718. Min Act: -0.0001

Data Index: 1423054 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1643702 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 1.3972. Min Range: -1.3972

Max Act: 1.2373. Min Act: -0.0001

Data Index: 1541618 (Python Code)

Max Activating Token Index: 113