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

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

Neuron 2330 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2682. Min Act: -0.0000

Data Index: 973033 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2668. Min Act: -0.0001

Data Index: 40181 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2355. Min Act: -0.0001

Data Index: 76678 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1242848 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1843. Min Act: -0.0001

Data Index: 627593 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1844. Min Act: -0.0001

Data Index: 591167 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1902. Min Act: -0.0001

Data Index: 225814 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1858. Min Act: -0.0001

Data Index: 386623 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1891. Min Act: -0.0001

Data Index: 443592 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1879. Min Act: -0.0001

Data Index: 913336 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1873. Min Act: -0.0000

Data Index: 372445 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1085692 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1813. Min Act: -0.0001

Data Index: 313157 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1678. Min Act: -0.0001

Data Index: 141606 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1083073 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1065699 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1595. Min Act: -0.0001

Data Index: 412040 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1542. Min Act: -0.0001

Data Index: 797151 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1340564 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.2682. Min Range: -0.2682

Max Act: 0.1473. Min Act: -0.0001

Data Index: 451356 (C4 (Web Text))

Max Activating Token Index: 247