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

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

Neuron 703 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: 0.4388. Min Range: -0.4388

Max Act: 0.4388. Min Act: -0.0001

Data Index: 707350 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3537. Min Act: -0.0001

Data Index: 676931 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.4154. Min Act: -0.0001

Data Index: 657354 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3577. Min Act: -0.0001

Data Index: 1206085 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3629. Min Act: -0.0001

Data Index: 1022718 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3340. Min Act: -0.0001

Data Index: 341867 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3891. Min Act: -0.0001

Data Index: 1162233 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3476. Min Act: -0.0001

Data Index: 796906 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3601. Min Act: -0.0001

Data Index: 1043984 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3509. Min Act: -0.0001

Data Index: 95781 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3088. Min Act: -0.0001

Data Index: 871298 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3513. Min Act: -0.0001

Data Index: 607506 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3296. Min Act: -0.0001

Data Index: 1266339 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3010. Min Act: -0.0001

Data Index: 549050 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3611. Min Act: -0.0001

Data Index: 714578 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3175. Min Act: -0.0001

Data Index: 908989 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2858. Min Act: -0.0001

Data Index: 585442 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3200. Min Act: -0.0001

Data Index: 249108 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1121246 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3255. Min Act: -0.0001

Data Index: 958853 (C4 (Web Text))

Max Activating Token Index: 17