Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1303 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: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0002

Data Index: 879628 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1316278 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1063265 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1325777 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0617. Min Act: -0.0002

Data Index: 668599 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0650. Min Act: -0.0002

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1096851 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0652. Min Act: -0.0002

Data Index: 62071 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1309756 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1138946 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0634. Min Act: -0.0002

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0624. Min Act: -0.0002

Data Index: 39247 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0593. Min Act: -0.0002

Data Index: 289660 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0601. Min Act: -0.0002

Data Index: 380674 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0616. Min Act: -0.0002

Data Index: 536201 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0614. Min Act: -0.0002

Data Index: 247133 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0606. Min Act: -0.0002

Data Index: 842803 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1355344 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1210964 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0603. Min Act: -0.0001

Data Index: 705830 (C4 (Web Text))

Max Activating Token Index: 643