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

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

Neuron 3767 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1502642 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1612026 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1400952 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1516896 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1369060 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1497584 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1401561 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1408549 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1509238 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1411966 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1486448 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1541922 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1387128 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1474617 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1621683 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1636918 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1581359 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1506912 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1417158 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1599541 (Python Code)

Max Activating Token Index: 19