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

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

Neuron 3676 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: 0.7608. Min Range: -0.7608

Max Act: 0.7266. Min Act: -0.0001

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7143. Min Act: -0.0000

Data Index: 842273 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7162. Min Act: -0.0001

Data Index: 1144661 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6853. Min Act: -0.0001

Data Index: 255754 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1288223 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.7608. Min Act: -0.0000

Data Index: 814794 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1092897 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6649. Min Act: -0.0001

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6606. Min Act: -0.0000

Data Index: 560906 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6571. Min Act: -0.0001

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6756. Min Act: -0.0001

Data Index: 292507 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6482. Min Act: -0.0001

Data Index: 196708 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6479. Min Act: -0.0001

Data Index: 798333 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6684. Min Act: -0.0001

Data Index: 1070516 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6671. Min Act: -0.0001

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6162. Min Act: -0.0000

Data Index: 821868 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6359. Min Act: -0.0001

Data Index: 155084 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1165644 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6289. Min Act: -0.0001

Data Index: 1024286 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6268. Min Act: -0.0001

Data Index: 554266 (C4 (Web Text))

Max Activating Token Index: 452