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

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

Neuron 616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0917. Min Act: -0.0001

Data Index: 135033 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0895. Min Act: -0.0000

Data Index: 640381 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0794. Min Act: -0.0000

Data Index: 806322 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1599171 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1364084 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1555227 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1571489 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1487022 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1385917 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1016023 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0744. Min Act: -0.0001

Data Index: 385446 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1577079 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1597691 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0656. Min Act: -0.0000

Data Index: 337550 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1482526 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1571800 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1622749 (Python Code)

Max Activating Token Index: 727

Text #17

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1604754 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1616034 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1550650 (Python Code)

Max Activating Token Index: 133