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

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

Neuron 5354 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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0002

Data Index: 11600 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0697. Min Act: -0.0002

Data Index: 438883 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0649. Min Act: -0.0002

Data Index: 82409 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1089141 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0662. Min Act: -0.0002

Data Index: 216786 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0647. Min Act: -0.0002

Data Index: 396619 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1309984 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1224542 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0625. Min Act: -0.0002

Data Index: 572996 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0626. Min Act: -0.0002

Data Index: 162178 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0629. Min Act: -0.0002

Data Index: 543441 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1436 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0620. Min Act: -0.0002

Data Index: 12789 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1363927 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0622. Min Act: -0.0002

Data Index: 405378 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1259941 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1608339 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0592. Min Act: -0.0002

Data Index: 483346 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0592. Min Act: -0.0002

Data Index: 99417 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1107548 (C4 (Web Text))

Max Activating Token Index: 787