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

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

Neuron 1897 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: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0003

Data Index: 642720 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0603. Min Act: -0.0002

Data Index: 875041 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0576. Min Act: -0.0003

Data Index: 241837 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1568657 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1070966 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0566. Min Act: -0.0003

Data Index: 746661 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0559. Min Act: -0.0003

Data Index: 883397 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0548. Min Act: -0.0003

Data Index: 294826 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0538. Min Act: -0.0003

Data Index: 764650 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0530. Min Act: -0.0003

Data Index: 501956 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0515. Min Act: -0.0003

Data Index: 651975 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1086213 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0497. Min Act: -0.0002

Data Index: 277195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0508. Min Act: -0.0002

Data Index: 2906 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0487. Min Act: -0.0003

Data Index: 247190 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1209210 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0514. Min Act: -0.0002

Data Index: 740991 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0495. Min Act: -0.0003

Data Index: 639174 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0503. Min Act: -0.0003

Data Index: 500946 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0486. Min Act: -0.0003

Data Index: 639797 (C4 (Web Text))

Max Activating Token Index: 903