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

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

Neuron 19 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2337. Min Act: -0.0001

Data Index: 984114 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1099387 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1143516 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2085. Min Act: -0.0001

Data Index: 152650 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1870. Min Act: -0.0001

Data Index: 241013 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1969. Min Act: -0.0001

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1303088 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1840. Min Act: -0.0001

Data Index: 930637 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1166346 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1667. Min Act: -0.0001

Data Index: 383768 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1690. Min Act: -0.0001

Data Index: 194699 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1658. Min Act: -0.0001

Data Index: 424560 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1127647 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1687. Min Act: -0.0001

Data Index: 743854 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1606. Min Act: -0.0001

Data Index: 652510 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1592. Min Act: -0.0001

Data Index: 575351 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1330. Min Act: -0.0001

Data Index: 390024 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1043527 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1630. Min Act: -0.0001

Data Index: 836495 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1602. Min Act: -0.0001

Data Index: 508391 (C4 (Web Text))

Max Activating Token Index: 315