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

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

Neuron 3820 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: 1.1953. Min Range: -1.1953

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1526995 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1547524 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1437352 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1393465 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1515970 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1614807 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1468739 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1575371 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1604245 (Python Code)

Max Activating Token Index: 110

Text #9

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1513402 (Python Code)

Max Activating Token Index: 971

Text #10

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1460790 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1648884 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1381655 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 1.1953. Min Range: -1.1953

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1543450 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1474012 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1412627 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1394688 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1594483 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1394700 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 1.1953. Min Range: -1.1953

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1410854 (Python Code)

Max Activating Token Index: 752