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

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

Neuron 4844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1175269 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1008. Min Act: -0.0000

Data Index: 125234 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0812. Min Act: -0.0000

Data Index: 347348 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0873. Min Act: -0.0000

Data Index: 361798 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0845. Min Act: -0.0000

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0787. Min Act: -0.0000

Data Index: 737565 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0772. Min Act: -0.0000

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1017610 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0739. Min Act: -0.0000

Data Index: 81788 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0810. Min Act: -0.0000

Data Index: 711435 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0690. Min Act: -0.0000

Data Index: 184682 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0636. Min Act: -0.0000

Data Index: 378684 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1211869 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1137376 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0651. Min Act: -0.0000

Data Index: 244060 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1585993 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0635. Min Act: -0.0000

Data Index: 463489 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0633. Min Act: -0.0000

Data Index: 492094 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1643207 (Python Code)

Max Activating Token Index: 945