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

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

Neuron 239 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: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0001

Data Index: 575665 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1308483 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1859. Min Act: -0.0001

Data Index: 871384 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1326231 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1242799 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1714. Min Act: -0.0001

Data Index: 688152 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1540. Min Act: -0.0001

Data Index: 476151 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1573. Min Act: -0.0001

Data Index: 59370 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1618. Min Act: -0.0001

Data Index: 156132 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1636. Min Act: -0.0001

Data Index: 16019 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1006846 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1581. Min Act: -0.0001

Data Index: 188547 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1554. Min Act: -0.0001

Data Index: 27994 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1493. Min Act: -0.0001

Data Index: 747498 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1519. Min Act: -0.0001

Data Index: 680971 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1345309 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1434. Min Act: -0.0001

Data Index: 524245 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1456. Min Act: -0.0001

Data Index: 944514 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1358. Min Act: -0.0001

Data Index: 688980 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1298. Min Act: -0.0001

Data Index: 954809 (C4 (Web Text))

Max Activating Token Index: 263