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

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

Neuron 3834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.5005. Min Act: -0.0000

Data Index: 983970 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4779. Min Act: -0.0000

Data Index: 136742 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1462122 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1083470 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1622922 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.4005. Min Act: -0.0000

Data Index: 262778 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3898. Min Act: -0.0000

Data Index: 509056 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1295208 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3577. Min Act: -0.0000

Data Index: 494299 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3911. Min Act: -0.0000

Data Index: 56466 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1279580 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1016595 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3770. Min Act: -0.0000

Data Index: 5457 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1281085 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1578626 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1504470 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3430. Min Act: -0.0000

Data Index: 152331 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3386. Min Act: -0.0000

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3487. Min Act: -0.0000

Data Index: 252313 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.5005. Min Range: -0.5005

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1591056 (Python Code)

Max Activating Token Index: 843