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

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

Neuron 3838 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: 0.7551. Min Range: -0.7551

Max Act: 0.7373. Min Act: -0.0001

Data Index: 210642 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7551. Min Act: -0.0001

Data Index: 504125 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1011637 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1288672 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.7432. Min Act: -0.0001

Data Index: 871053 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6662. Min Act: -0.0001

Data Index: 755126 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6744. Min Act: -0.0001

Data Index: 834624 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6699. Min Act: -0.0001

Data Index: 36119 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6575. Min Act: -0.0001

Data Index: 764571 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6747. Min Act: -0.0001

Data Index: 19075 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6310. Min Act: -0.0001

Data Index: 398443 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.5927. Min Act: -0.0001

Data Index: 709734 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6027. Min Act: -0.0001

Data Index: 10709 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6053. Min Act: -0.0001

Data Index: 275435 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6647. Min Act: -0.0001

Data Index: 970170 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6462. Min Act: -0.0001

Data Index: 253447 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6458. Min Act: -0.0001

Data Index: 833820 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6606. Min Act: -0.0001

Data Index: 204373 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6187. Min Act: -0.0001

Data Index: 935060 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.7551. Min Range: -0.7551

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1344583 (C4 (Web Text))

Max Activating Token Index: 510