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

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

Neuron 4 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: 1.7339. Min Range: -1.7339

Max Act: 1.7339. Min Act: -0.0000

Data Index: 1475887 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.5538. Min Act: -0.0000

Data Index: 1443049 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.5198. Min Act: -0.0000

Data Index: 1586699 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1514711 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1473833 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2843. Min Act: -0.0000

Data Index: 78837 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1471613 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2217. Min Act: -0.0000

Data Index: 111867 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2405. Min Act: -0.0000

Data Index: 543423 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1364953 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1386989 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1325070 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2015. Min Act: -0.0000

Data Index: 915774 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1641268 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1120661 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1392089 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1491694 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1066880 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1154620 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.7339. Min Range: -1.7339

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1045204 (C4 (Web Text))

Max Activating Token Index: 280