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

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

Neuron 3782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0000

Data Index: 94127 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0665. Min Act: -0.0000

Data Index: 128670 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1267308 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0713. Min Act: -0.0000

Data Index: 333698 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0661. Min Act: -0.0000

Data Index: 435711 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0637. Min Act: -0.0000

Data Index: 185266 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1219427 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0656. Min Act: -0.0001

Data Index: 683979 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0703. Min Act: -0.0000

Data Index: 57542 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1073240 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1043008 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0608. Min Act: -0.0000

Data Index: 225905 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0630. Min Act: -0.0000

Data Index: 350130 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0621. Min Act: -0.0000

Data Index: 748671 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1184935 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0591. Min Act: -0.0000

Data Index: 117806 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0612. Min Act: -0.0000

Data Index: 175451 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0560. Min Act: -0.0000

Data Index: 340096 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0582. Min Act: -0.0000

Data Index: 696738 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1208243 (C4 (Web Text))

Max Activating Token Index: 504