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

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

Neuron 5229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1565. Min Act: -0.0001

Data Index: 374893 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1372. Min Act: -0.0001

Data Index: 311643 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1509. Min Act: -0.0001

Data Index: 486400 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1451. Min Act: -0.0002

Data Index: 753412 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1488. Min Act: -0.0001

Data Index: 487054 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1475. Min Act: -0.0001

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1380. Min Act: -0.0001

Data Index: 85760 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1361. Min Act: -0.0001

Data Index: 984989 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1342288 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1346. Min Act: -0.0001

Data Index: 316105 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1251. Min Act: -0.0001

Data Index: 578945 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1137994 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1359. Min Act: -0.0001

Data Index: 41064 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1347. Min Act: -0.0001

Data Index: 441026 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1423. Min Act: -0.0001

Data Index: 875606 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1398. Min Act: -0.0001

Data Index: 528590 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1267. Min Act: -0.0001

Data Index: 997736 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1183415 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1307. Min Act: -0.0001

Data Index: 244729 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1496. Min Act: -0.0001

Data Index: 36002 (C4 (Web Text))

Max Activating Token Index: 912