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

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

Neuron 5382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0907. Min Range: -5.0907

Max Act: 5.0907. Min Act: -0.0000

Data Index: 28198 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.5525. Min Act: -0.0000

Data Index: 1307795 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.1041. Min Act: -0.0000

Data Index: 560699 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.3844. Min Act: -0.0000

Data Index: 704136 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.2922. Min Act: -0.0000

Data Index: 1187668 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.0647. Min Act: -0.0000

Data Index: 430429 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.2501. Min Act: -0.0000

Data Index: 840529 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.1864. Min Act: -0.0000

Data Index: 960955 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.3508. Min Act: -0.0000

Data Index: 1339101 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.0891. Min Act: -0.0000

Data Index: 111326 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.5736. Min Act: -0.0000

Data Index: 577549 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.0352. Min Act: -0.0000

Data Index: 242009 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 5.0907. Min Range: -5.0907

Max Act: 4.1492. Min Act: -0.0000

Data Index: 1225114 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.8852. Min Act: -0.0000

Data Index: 1336027 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.7281. Min Act: -0.0000

Data Index: 209698 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1350991 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.7128. Min Act: -0.0000

Data Index: 638854 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.9967. Min Act: -0.0000

Data Index: 863678 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.8000. Min Act: -0.0000

Data Index: 162629 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 5.0907. Min Range: -5.0907

Max Act: 3.9513. Min Act: -0.0000

Data Index: 1342001 (C4 (Web Text))

Max Activating Token Index: 211