Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1224757 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0609. Min Act: -0.0001

Data Index: 394572 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0557. Min Act: -0.0001

Data Index: 922645 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0614. Min Act: -0.0001

Data Index: 80422 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0588. Min Act: -0.0001

Data Index: 417804 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1246865 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1129177 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1404612 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0591. Min Act: -0.0001

Data Index: 119297 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1303135 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0580. Min Act: -0.0001

Data Index: 113071 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0592. Min Act: -0.0001

Data Index: 445065 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0549. Min Act: -0.0001

Data Index: 664211 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1366370 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0567. Min Act: -0.0001

Data Index: 331612 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0494. Min Act: -0.0001

Data Index: 379667 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0532. Min Act: -0.0001

Data Index: 444154 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0563. Min Act: -0.0001

Data Index: 783484 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1118009 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1505040 (Python Code)

Max Activating Token Index: 35