Model: SoLU Model: 4 Layers, 2048 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-4l')

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1079604 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0705. Min Act: -0.0002

Data Index: 8691 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0724. Min Act: -0.0002

Data Index: 345762 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0635. Min Act: -0.0002

Data Index: 933386 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0632. Min Act: -0.0002

Data Index: 448325 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1093216 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1029192 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0619. Min Act: -0.0001

Data Index: 546461 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0579. Min Act: -0.0002

Data Index: 758985 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0587. Min Act: -0.0001

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1017035 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0594. Min Act: -0.0002

Data Index: 676944 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0571. Min Act: -0.0002

Data Index: 44653 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1011041 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1109464 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0551. Min Act: -0.0002

Data Index: 987989 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0563. Min Act: -0.0002

Data Index: 402027 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0562. Min Act: -0.0002

Data Index: 147772 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1084394 (C4 (Web Text))

Max Activating Token Index: 126