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

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

Neuron 2642 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.8336. Min Act: -0.0000

Data Index: 472043 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1297009 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1264246 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5908. Min Act: -0.0000

Data Index: 278443 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1287606 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5823. Min Act: -0.0000

Data Index: 888918 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5426. Min Act: -0.0000

Data Index: 527810 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5686. Min Act: -0.0000

Data Index: 593684 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5156. Min Act: -0.0000

Data Index: 457867 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4841. Min Act: -0.0000

Data Index: 194928 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4870. Min Act: -0.0000

Data Index: 558760 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4895. Min Act: -0.0000

Data Index: 587849 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4757. Min Act: -0.0000

Data Index: 839844 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4338. Min Act: -0.0000

Data Index: 963499 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1058688 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.5012. Min Act: -0.0000

Data Index: 165933 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1233476 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4755. Min Act: -0.0000

Data Index: 884348 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1156705 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.8336. Min Range: -0.8336

Max Act: 0.4379. Min Act: -0.0000

Data Index: 133900 (C4 (Web Text))

Max Activating Token Index: 220