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

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

Neuron 2536 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: 1.5779. Min Range: -1.5779

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1368456 (Python Code)

Max Activating Token Index: 376

Text #1

Max Range: 1.5779. Min Range: -1.5779

Max Act: 1.4086. Min Act: -0.0000

Data Index: 1391287 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 1.5779. Min Range: -1.5779

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1479494 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 1.5779. Min Range: -1.5779

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1434397 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 1.5779. Min Range: -1.5779

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1496023 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 1.5779. Min Range: -1.5779

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1626909 (Python Code)

Max Activating Token Index: 579

Text #6

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1459108 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1368271 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1646366 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1368053 (Python Code)

Max Activating Token Index: 232

Text #10

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1530239 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1522306 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1446854 (Python Code)

Max Activating Token Index: 928

Text #13

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1363371 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1617985 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1437816 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1563520 (Python Code)

Max Activating Token Index: 960

Text #17

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1393553 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1456386 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 1.5779. Min Range: -1.5779

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1587875 (Python Code)

Max Activating Token Index: 680