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

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

Neuron 1735 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: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 861767 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0561. Min Act: -0.0002

Data Index: 289002 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0579. Min Act: -0.0002

Data Index: 220319 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1018171 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0539. Min Act: -0.0002

Data Index: 249860 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0519. Min Act: -0.0002

Data Index: 402829 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0508. Min Act: -0.0002

Data Index: 457990 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0522. Min Act: -0.0002

Data Index: 421833 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0523. Min Act: -0.0002

Data Index: 883665 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1219006 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0521. Min Act: -0.0002

Data Index: 156688 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1083886 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1009626 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1479639 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1081877 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1141943 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0468. Min Act: -0.0002

Data Index: 634666 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0481. Min Act: -0.0002

Data Index: 607607 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1247847 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0458. Min Act: -0.0002

Data Index: 888265 (C4 (Web Text))

Max Activating Token Index: 26