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

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

Neuron 3070 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: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1411684 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1546217 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0707. Min Act: -0.0001

Data Index: 917921 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0632. Min Act: -0.0001

Data Index: 588929 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0615. Min Act: -0.0001

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1417104 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1239410 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0567. Min Act: -0.0001

Data Index: 902461 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0642. Min Act: -0.0001

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1272768 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0593. Min Act: -0.0001

Data Index: 187330 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0573. Min Act: -0.0001

Data Index: 496991 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0529. Min Act: -0.0001

Data Index: 203556 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0548. Min Act: -0.0001

Data Index: 917054 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0545. Min Act: -0.0001

Data Index: 507114 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0568. Min Act: -0.0001

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0536. Min Act: -0.0001

Data Index: 777597 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0533. Min Act: -0.0001

Data Index: 282586 (C4 (Web Text))

Max Activating Token Index: 8