Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0001

Data Index: 861002 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0664. Min Act: -0.0001

Data Index: 513033 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1553809 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1084959 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0639. Min Act: -0.0000

Data Index: 969445 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0609. Min Act: -0.0000

Data Index: 233431 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0631. Min Act: -0.0001

Data Index: 792600 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1395446 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1109035 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1634733 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0563. Min Act: -0.0000

Data Index: 710921 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0556. Min Act: -0.0001

Data Index: 992347 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0541. Min Act: -0.0001

Data Index: 772954 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1457512 (Python Code)

Max Activating Token Index: 821

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0537. Min Act: -0.0000

Data Index: 34625 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0517. Min Act: -0.0001

Data Index: 363958 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1019771 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0558. Min Act: -0.0000

Data Index: 418849 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1068553 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0460. Min Act: -0.0001

Data Index: 629126 (C4 (Web Text))

Max Activating Token Index: 859