Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3980 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1542925 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1648519 (Python Code)

Max Activating Token Index: 924

Text #2

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1429329 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1419963 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2067. Min Act: -0.0001

Data Index: 1400379 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1442737 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1809. Min Act: -0.0001

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1588778 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1548937 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1368006 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1436571 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1497703 (Python Code)

Max Activating Token Index: 175

Text #14

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1588282 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1600896 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1463019 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1765. Min Act: -0.0000

Data Index: 896337 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1822. Min Act: -0.0001

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1514841 (Python Code)

Max Activating Token Index: 307