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

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

Neuron 448 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: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0002

Data Index: 441489 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0637. Min Act: -0.0003

Data Index: 150706 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0625. Min Act: -0.0003

Data Index: 349018 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0615. Min Act: -0.0003

Data Index: 721412 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0631. Min Act: -0.0004

Data Index: 1047963 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0578. Min Act: -0.0004

Data Index: 701906 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0551. Min Act: -0.0004

Data Index: 827427 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0545. Min Act: -0.0003

Data Index: 72660 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0550. Min Act: -0.0003

Data Index: 11692 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0537. Min Act: -0.0004

Data Index: 250874 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1034408 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0546. Min Act: -0.0003

Data Index: 276968 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0486. Min Act: -0.0003

Data Index: 299915 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0526. Min Act: -0.0003

Data Index: 451259 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1027200 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0518. Min Act: -0.0004

Data Index: 587892 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0509. Min Act: -0.0003

Data Index: 471946 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0507. Min Act: -0.0002

Data Index: 665801 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0497. Min Act: -0.0003

Data Index: 68339 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1181681 (C4 (Web Text))

Max Activating Token Index: 701