Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2836 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1567536 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1552287 (Python Code)

Max Activating Token Index: 249

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1446803 (Python Code)

Max Activating Token Index: 186

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1410476 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1444821 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1619135 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1479784 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1383430 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1518604 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1506728 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1613057 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1621956 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1389634 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1441570 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1567765 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1613820 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1414589 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1460254 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1468836 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1459553 (Python Code)

Max Activating Token Index: 145