Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0911. Min Act: -0.0000

Data Index: 701224 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1199944 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0799. Min Act: 0.0000

Data Index: 467166 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1077398 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0776. Min Act: -0.0000

Data Index: 657739 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0741. Min Act: -0.0000

Data Index: 977520 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1357499 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0766. Min Act: -0.0000

Data Index: 118249 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1310711 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0763. Min Act: -0.0000

Data Index: 762614 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1286574 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0723. Min Act: -0.0000

Data Index: 396977 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0738. Min Act: 0.0000

Data Index: 1029489 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0662. Min Act: -0.0000

Data Index: 400009 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0655. Min Act: -0.0000

Data Index: 668216 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1643172 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1008551 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0688. Min Act: -0.0000

Data Index: 822118 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0680. Min Act: -0.0000

Data Index: 668637 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1165613 (C4 (Web Text))

Max Activating Token Index: 498