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

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

Neuron 1792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1727. Min Act: -0.0003

Data Index: 738869 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1692. Min Act: -0.0002

Data Index: 538434 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1606. Min Act: -0.0003

Data Index: 268669 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1543. Min Act: -0.0003

Data Index: 1349856 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1593. Min Act: -0.0003

Data Index: 820668 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1591. Min Act: -0.0003

Data Index: 1034881 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1536. Min Act: -0.0003

Data Index: 622310 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1494. Min Act: -0.0003

Data Index: 1086803 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1551. Min Act: -0.0002

Data Index: 600884 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1487. Min Act: -0.0004

Data Index: 883716 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1490. Min Act: -0.0004

Data Index: 304632 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1472. Min Act: -0.0004

Data Index: 183613 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1465. Min Act: -0.0003

Data Index: 1080032 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1411. Min Act: -0.0003

Data Index: 1055833 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1246371 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1448. Min Act: -0.0003

Data Index: 1174736 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1401. Min Act: -0.0003

Data Index: 735132 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1445. Min Act: -0.0004

Data Index: 216486 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1485. Min Act: -0.0004

Data Index: 1266333 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1451. Min Act: -0.0003

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 795