Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 797 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0604. Min Act: -0.0004

Data Index: 541554 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0690. Min Act: -0.0004

Data Index: 479482 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0767. Min Act: -0.0004

Data Index: 760995 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0004

Data Index: 1463465 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0595. Min Act: -0.0004

Data Index: 1045643 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0657. Min Act: -0.0004

Data Index: 1076127 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0610. Min Act: -0.0004

Data Index: 394911 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0433. Min Act: -0.0004

Data Index: 133717 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0676. Min Act: -0.0004

Data Index: 655839 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0488. Min Act: -0.0004

Data Index: 1300859 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0725. Min Act: -0.0004

Data Index: 1038282 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0522. Min Act: -0.0004

Data Index: 1406312 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0563. Min Act: -0.0004

Data Index: 1052325 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0485. Min Act: -0.0004

Data Index: 702750 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0546. Min Act: -0.0004

Data Index: 924174 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1111152 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0582. Min Act: -0.0004

Data Index: 1073597 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0562. Min Act: -0.0004

Data Index: 923170 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0606. Min Act: -0.0004

Data Index: 905581 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0581. Min Act: -0.0004

Data Index: 1039871 (C4 (Web Text))

Max Activating Token Index: 814