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

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

Neuron 2646 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: 0.3696. Min Range: -0.3696

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1031107 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3135. Min Act: -0.0001

Data Index: 587502 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2768. Min Act: -0.0001

Data Index: 364077 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3351. Min Act: -0.0001

Data Index: 139618 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1113573 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2747. Min Act: -0.0001

Data Index: 560159 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2815. Min Act: -0.0001

Data Index: 577491 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2715. Min Act: -0.0001

Data Index: 676569 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3093. Min Act: -0.0001

Data Index: 982156 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2895. Min Act: -0.0001

Data Index: 1201326 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1241296 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2921. Min Act: -0.0001

Data Index: 660743 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2845. Min Act: -0.0001

Data Index: 855424 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1222503 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2772. Min Act: -0.0001

Data Index: 632827 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2963. Min Act: -0.0001

Data Index: 845886 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2748. Min Act: -0.0001

Data Index: 529614 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2370. Min Act: -0.0001

Data Index: 569676 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2650. Min Act: -0.0001

Data Index: 618625 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2841. Min Act: -0.0001

Data Index: 519206 (C4 (Web Text))

Max Activating Token Index: 245