Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3214 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0003

Data Index: 840097 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1037324 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0704. Min Act: -0.0003

Data Index: 740254 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1503641 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0646. Min Act: -0.0002

Data Index: 625119 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1623309 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1342522 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0556. Min Act: -0.0002

Data Index: 775145 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0554. Min Act: -0.0002

Data Index: 15684 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1578877 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0541. Min Act: -0.0003

Data Index: 498780 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0539. Min Act: -0.0002

Data Index: 516893 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1245265 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0534. Min Act: -0.0003

Data Index: 64025 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1350893 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1433974 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0531. Min Act: -0.0003

Data Index: 661319 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0530. Min Act: -0.0002

Data Index: 586523 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0528. Min Act: -0.0003

Data Index: 807162 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1085315 (C4 (Web Text))

Max Activating Token Index: 808