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

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

Neuron 4510 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.3708. Min Act: -0.0000

Data Index: 1527932 (Python Code)

Max Activating Token Index: 433

Text #1

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.2989. Min Act: -0.0000

Data Index: 1561552 (Python Code)

Max Activating Token Index: 884

Text #2

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.2283. Min Act: -0.0000

Data Index: 1401892 (Python Code)

Max Activating Token Index: 366

Text #3

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.1258. Min Act: -0.0000

Data Index: 55770 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.1119. Min Act: -0.0000

Data Index: 1560407 (Python Code)

Max Activating Token Index: 463

Text #5

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.0566. Min Act: -0.0000

Data Index: 1501800 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.0382. Min Act: -0.0000

Data Index: 9658 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1292662 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 2.3708. Min Range: -2.3708

Max Act: 2.1211. Min Act: -0.0000

Data Index: 558986 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.9471. Min Act: -0.0000

Data Index: 1631468 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.9000. Min Act: -0.0000

Data Index: 468292 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.8911. Min Act: -0.0000

Data Index: 612760 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.8126. Min Act: -0.0000

Data Index: 1466159 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.8184. Min Act: -0.0000

Data Index: 1435215 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.6784. Min Act: -0.0000

Data Index: 308084 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.8013. Min Act: -0.0000

Data Index: 731690 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.7830. Min Act: -0.0000

Data Index: 862659 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.7840. Min Act: -0.0000

Data Index: 811375 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.7180. Min Act: -0.0000

Data Index: 521613 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.3708. Min Range: -2.3708

Max Act: 1.7260. Min Act: -0.0000

Data Index: 32339 (C4 (Web Text))

Max Activating Token Index: 701