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

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

Neuron 1620 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.4640. Min Act: -0.0000

Data Index: 1193161 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.5086. Min Act: -0.0000

Data Index: 368727 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.6586. Min Act: -0.0000

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.4340. Min Act: -0.0000

Data Index: 413413 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3096. Min Act: -0.0000

Data Index: 107288 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3434. Min Act: -0.0000

Data Index: 133151 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3401. Min Act: -0.0000

Data Index: 843991 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1266386 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2759. Min Act: -0.0000

Data Index: 1151790 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2619. Min Act: -0.0000

Data Index: 139345 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2232. Min Act: -0.0000

Data Index: 697792 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1334064 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2433. Min Act: -0.0000

Data Index: 229715 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2804. Min Act: -0.0000

Data Index: 903412 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1122319 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3100. Min Act: -0.0000

Data Index: 1121096 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1162205 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.1873. Min Act: -0.0000

Data Index: 459692 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.2386. Min Act: -0.0000

Data Index: 745416 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 1.6586. Min Range: -1.6586

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1054085 (C4 (Web Text))

Max Activating Token Index: 459