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

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

Neuron 335 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.3261. Min Act: -0.0001

Data Index: 1347186 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.2524. Min Act: -0.0001

Data Index: 601231 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.4087. Min Act: -0.0001

Data Index: 958271 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0345. Min Act: -0.0001

Data Index: 732767 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.2173. Min Act: -0.0001

Data Index: 527762 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0413. Min Act: -0.0001

Data Index: 1028772 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 1.4087. Min Range: -1.4087

Max Act: 0.9659. Min Act: -0.0001

Data Index: 451108 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0494. Min Act: -0.0001

Data Index: 117893 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.3233. Min Act: -0.0001

Data Index: 160997 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.4087. Min Range: -1.4087

Max Act: 0.9655. Min Act: -0.0001

Data Index: 208532 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1567. Min Act: -0.0001

Data Index: 519704 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.2026. Min Act: -0.0001

Data Index: 725691 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1442. Min Act: -0.0001

Data Index: 338665 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0297. Min Act: -0.0001

Data Index: 273453 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1728. Min Act: -0.0001

Data Index: 1011547 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1599. Min Act: -0.0001

Data Index: 285749 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0909. Min Act: -0.0001

Data Index: 291925 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1222. Min Act: -0.0001

Data Index: 431505 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.1589. Min Act: -0.0001

Data Index: 1055077 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 1.4087. Min Range: -1.4087

Max Act: 1.0648. Min Act: -0.0001

Data Index: 1070548 (C4 (Web Text))

Max Activating Token Index: 891