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

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

Neuron 3764 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: 1.2829. Min Range: -1.2829

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1584895 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1516409 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1512904 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1597071 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1569339 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1616445 (Python Code)

Max Activating Token Index: 936

Text #6

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1528336 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1456129 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1474907 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1537434 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1495345 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1650010 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1394430 (Python Code)

Max Activating Token Index: 686

Text #13

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1561892 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1584830 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1595121 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1512465 (Python Code)

Max Activating Token Index: 367

Text #17

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1404268 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1611876 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1369184 (Python Code)

Max Activating Token Index: 863