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

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

Neuron 4345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.2237. Min Act: -0.0001

Data Index: 64020 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1059479 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1913. Min Act: -0.0001

Data Index: 276001 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1773. Min Act: -0.0000

Data Index: 799155 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1921. Min Act: -0.0001

Data Index: 57154 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1737. Min Act: -0.0001

Data Index: 709603 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1794. Min Act: -0.0001

Data Index: 392532 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1028193 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1318644 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1805. Min Act: -0.0001

Data Index: 661584 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1733. Min Act: -0.0000

Data Index: 925267 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1228042 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1641. Min Act: -0.0001

Data Index: 465152 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1640. Min Act: -0.0001

Data Index: 43032 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1095833 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1597. Min Act: -0.0001

Data Index: 525323 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1158315 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1674. Min Act: -0.0001

Data Index: 911757 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1248339 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.2237. Min Range: -0.2237

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1235949 (C4 (Web Text))

Max Activating Token Index: 656