Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1717 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0006

Data Index: 358908 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0789. Min Act: -0.0006

Data Index: 1036234 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0741. Min Act: -0.0006

Data Index: 129748 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0741. Min Act: -0.0006

Data Index: 82962 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0729. Min Act: -0.0006

Data Index: 464894 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0715. Min Act: -0.0006

Data Index: 707964 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0695. Min Act: -0.0006

Data Index: 893053 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0676. Min Act: -0.0006

Data Index: 873094 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0631. Min Act: -0.0006

Data Index: 51731 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1347 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0620. Min Act: -0.0006

Data Index: 549562 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0607. Min Act: -0.0006

Data Index: 621824 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0669. Min Act: -0.0006

Data Index: 443354 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0624. Min Act: -0.0006

Data Index: 877970 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0613. Min Act: -0.0006

Data Index: 696218 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0635. Min Act: -0.0005

Data Index: 1086530 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0552. Min Act: -0.0006

Data Index: 295874 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0606. Min Act: -0.0006

Data Index: 379979 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0614. Min Act: -0.0006

Data Index: 505681 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0645. Min Act: -0.0006

Data Index: 1309570 (C4 (Web Text))

Max Activating Token Index: 225