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

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

Neuron 4111 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1374763 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1646579 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.6639. Min Act: -0.0000

Data Index: 1474480 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1623016 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1447524 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1545427 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1569835 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1417366 (Python Code)

Max Activating Token Index: 990

Text #8

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1526791 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1436615 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1475046 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1445524 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1623792 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1540129 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 1.7990. Min Range: -1.7990

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1642710 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1360349 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1634659 (Python Code)

Max Activating Token Index: 735

Text #17

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1360870 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1520761 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 1.7990. Min Range: -1.7990

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1416136 (Python Code)

Max Activating Token Index: 710