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

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

Neuron 2928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0002

Data Index: 465671 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0615. Min Act: -0.0002

Data Index: 267730 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1005941 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0572. Min Act: -0.0002

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0607. Min Act: -0.0002

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1325622 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0535. Min Act: -0.0002

Data Index: 87502 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0505. Min Act: -0.0002

Data Index: 178286 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1225698 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0558. Min Act: -0.0002

Data Index: 517220 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0536. Min Act: -0.0002

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0481. Min Act: -0.0002

Data Index: 47146 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1079020 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0486. Min Act: -0.0002

Data Index: 130109 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0539. Min Act: -0.0002

Data Index: 103995 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0469. Min Act: -0.0002

Data Index: 300251 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0450. Min Act: -0.0002

Data Index: 752446 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1220657 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0443. Min Act: -0.0002

Data Index: 323784 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0511. Min Act: -0.0002

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 238