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

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

Neuron 4986 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: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0001

Data Index: 218914 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0663. Min Act: -0.0001

Data Index: 853465 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0639. Min Act: -0.0001

Data Index: 699613 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0589. Min Act: -0.0001

Data Index: 656541 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0605. Min Act: -0.0001

Data Index: 898331 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0611. Min Act: -0.0001

Data Index: 578561 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0637. Min Act: -0.0001

Data Index: 135742 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0601. Min Act: -0.0001

Data Index: 25541 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0608. Min Act: -0.0001

Data Index: 504683 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0578. Min Act: -0.0001

Data Index: 977545 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0566. Min Act: -0.0001

Data Index: 767430 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0556. Min Act: -0.0001

Data Index: 111470 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0544. Min Act: -0.0001

Data Index: 584270 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1046861 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0533. Min Act: -0.0001

Data Index: 595347 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1025982 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0499. Min Act: -0.0001

Data Index: 224129 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0533. Min Act: -0.0001

Data Index: 961426 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1311894 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0557. Min Act: -0.0001

Data Index: 342885 (C4 (Web Text))

Max Activating Token Index: 285