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

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

Neuron 5965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.6450. Min Act: -0.0000

Data Index: 1533913 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1590842 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1638548 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1416645 (Python Code)

Max Activating Token Index: 710

Text #4

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1459455 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1505942 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1420247 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1604031 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1582589 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1508189 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1446631 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1591323 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1516323 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1507599 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1380656 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1491356 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1490546 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1437568 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1625334 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 1.6450. Min Range: -1.6450

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1423710 (Python Code)

Max Activating Token Index: 871