Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1338188 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0000

Data Index: 149847 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0770. Min Act: -0.0000

Data Index: 676191 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0707. Min Act: -0.0000

Data Index: 595530 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0705. Min Act: -0.0000

Data Index: 398670 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1359073 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0653. Min Act: -0.0000

Data Index: 382550 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1115258 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0642. Min Act: -0.0000

Data Index: 29648 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0571. Min Act: -0.0000

Data Index: 454889 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0617. Min Act: -0.0000

Data Index: 125689 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1144643 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0543. Min Act: -0.0000

Data Index: 778490 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0543. Min Act: -0.0000

Data Index: 103216 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0614. Min Act: -0.0000

Data Index: 322101 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1025964 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0562. Min Act: -0.0000

Data Index: 826701 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0557. Min Act: -0.0000

Data Index: 752138 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1138646 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0538. Min Act: -0.0000

Data Index: 379677 (C4 (Web Text))

Max Activating Token Index: 283