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

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

Neuron 1189 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: 1.1859. Min Range: -1.1859

Max Act: 1.1859. Min Act: -0.0001

Data Index: 1032504 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.1859. Min Range: -1.1859

Max Act: 1.0580. Min Act: -0.0001

Data Index: 547553 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1595428 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 1.1859. Min Range: -1.1859

Max Act: 1.0505. Min Act: -0.0001

Data Index: 930871 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8803. Min Act: -0.0001

Data Index: 680374 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.1859. Min Range: -1.1859

Max Act: 1.0031. Min Act: -0.0001

Data Index: 204468 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.9371. Min Act: -0.0001

Data Index: 1030041 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1125533 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.9797. Min Act: -0.0001

Data Index: 1165409 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8774. Min Act: -0.0001

Data Index: 1586965 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8899. Min Act: -0.0000

Data Index: 357371 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1269084 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.9061. Min Act: -0.0001

Data Index: 905207 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8031. Min Act: -0.0001

Data Index: 647231 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8718. Min Act: -0.0001

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8868. Min Act: -0.0001

Data Index: 500772 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.9157. Min Act: -0.0001

Data Index: 194236 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8551. Min Act: -0.0000

Data Index: 936558 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8278. Min Act: -0.0001

Data Index: 311393 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 1.1859. Min Range: -1.1859

Max Act: 0.8462. Min Act: -0.0001

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 128