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

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

Neuron 2600 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0002

Data Index: 542804 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0836. Min Act: -0.0002

Data Index: 571423 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0764. Min Act: -0.0002

Data Index: 457964 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1110364 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0843. Min Act: -0.0002

Data Index: 25532 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1270151 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0703. Min Act: -0.0002

Data Index: 136998 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1437839 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1334694 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1342421 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0676. Min Act: -0.0002

Data Index: 793962 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0647. Min Act: -0.0002

Data Index: 179560 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0655. Min Act: -0.0002

Data Index: 482438 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0674. Min Act: -0.0002

Data Index: 803297 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0649. Min Act: -0.0002

Data Index: 933742 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0639. Min Act: -0.0002

Data Index: 519165 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0669. Min Act: -0.0002

Data Index: 213872 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0674. Min Act: -0.0002

Data Index: 55185 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0610. Min Act: -0.0002

Data Index: 324034 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1037905 (C4 (Web Text))

Max Activating Token Index: 608