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

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

Neuron 17 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: 0.9285. Min Range: -0.9285

Max Act: 0.9256. Min Act: -0.0001

Data Index: 1394506 (Python Code)

Max Activating Token Index: 868

Text #1

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.9102. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.9285. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7466. Min Act: -0.0001

Data Index: 503902 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7053. Min Act: -0.0001

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1167515 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7185. Min Act: -0.0001

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6977. Min Act: -0.0001

Data Index: 47652 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6966. Min Act: -0.0001

Data Index: 808406 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7207. Min Act: -0.0001

Data Index: 541870 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1042959 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7149. Min Act: -0.0001

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6955. Min Act: -0.0001

Data Index: 220037 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6723. Min Act: -0.0001

Data Index: 1030130 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7186. Min Act: -0.0001

Data Index: 614082 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6865. Min Act: -0.0001

Data Index: 157816 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6637. Min Act: -0.0001

Data Index: 511750 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6918. Min Act: -0.0001

Data Index: 1036050 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7138. Min Act: -0.0001

Data Index: 307846 (C4 (Web Text))

Max Activating Token Index: 631