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

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

Neuron 329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0003

Data Index: 877197 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0705. Min Act: -0.0003

Data Index: 968208 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1251875 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0665. Min Act: -0.0003

Data Index: 700422 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1193876 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1193988 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1314065 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0600. Min Act: -0.0003

Data Index: 876437 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0600. Min Act: -0.0003

Data Index: 11035 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0577. Min Act: -0.0003

Data Index: 659403 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0567. Min Act: -0.0003

Data Index: 862009 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0564. Min Act: -0.0003

Data Index: 760000 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1252973 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0543. Min Act: -0.0002

Data Index: 568980 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0546. Min Act: -0.0003

Data Index: 567337 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1131613 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0544. Min Act: -0.0003

Data Index: 850615 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0555. Min Act: -0.0003

Data Index: 937889 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0560. Min Act: -0.0002

Data Index: 795336 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0575. Min Act: -0.0003

Data Index: 484812 (C4 (Web Text))

Max Activating Token Index: 662