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

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

Neuron 688 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: 2.8695. Min Range: -2.8695

Max Act: 2.8695. Min Act: -0.0000

Data Index: 1626465 (Python Code)

Max Activating Token Index: 874

Text #1

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.6034. Min Act: -0.0000

Data Index: 1365685 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.6896. Min Act: -0.0000

Data Index: 1587224 (Python Code)

Max Activating Token Index: 637

Text #3

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1519093 (Python Code)

Max Activating Token Index: 439

Text #4

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.7491. Min Act: -0.0000

Data Index: 1554236 (Python Code)

Max Activating Token Index: 866

Text #5

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.4852. Min Act: -0.0000

Data Index: 1454095 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.4808. Min Act: -0.0000

Data Index: 1373382 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.2594. Min Act: -0.0000

Data Index: 1460971 (Python Code)

Max Activating Token Index: 739

Text #8

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.4619. Min Act: -0.0000

Data Index: 1370292 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.0481. Min Act: -0.0000

Data Index: 35831 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 2.8695. Min Range: -2.8695

Max Act: 2.0539. Min Act: -0.0000

Data Index: 704617 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1632009 (Python Code)

Max Activating Token Index: 272

Text #12

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8429. Min Act: -0.0000

Data Index: 860539 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1539588 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.7894. Min Act: -0.0000

Data Index: 996803 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8864. Min Act: -0.0000

Data Index: 341354 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8744. Min Act: -0.0000

Data Index: 590693 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.6592. Min Act: -0.0000

Data Index: 1587613 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8540. Min Act: -0.0000

Data Index: 1426773 (Python Code)

Max Activating Token Index: 519

Text #19

Max Range: 2.8695. Min Range: -2.8695

Max Act: 1.8513. Min Act: -0.0000

Data Index: 1486677 (Python Code)

Max Activating Token Index: 659