Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1829. Min Act: -0.0002

Data Index: 650102 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.2003. Min Act: -0.0002

Data Index: 942804 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1936. Min Act: -0.0002

Data Index: 220980 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1859. Min Act: -0.0002

Data Index: 89267 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1822. Min Act: -0.0002

Data Index: 1303409 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1770. Min Act: -0.0002

Data Index: 947397 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1750. Min Act: -0.0002

Data Index: 23138 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1105212 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1709. Min Act: -0.0002

Data Index: 480771 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1701. Min Act: -0.0002

Data Index: 85786 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1690. Min Act: -0.0002

Data Index: 777411 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1733. Min Act: -0.0002

Data Index: 997025 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1629. Min Act: -0.0002

Data Index: 432961 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1686. Min Act: -0.0002

Data Index: 277736 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1622. Min Act: -0.0002

Data Index: 1150779 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1513. Min Act: -0.0002

Data Index: 797051 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1590. Min Act: -0.0002

Data Index: 885044 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1568. Min Act: -0.0002

Data Index: 369797 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1554. Min Act: -0.0002

Data Index: 552408 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.2003. Min Range: -0.2003

Max Act: 0.1550. Min Act: -0.0002

Data Index: 726410 (C4 (Web Text))

Max Activating Token Index: 221