Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 645 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 267052 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0655. Min Act: -0.0003

Data Index: 640691 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1062571 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1101702 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0636. Min Act: -0.0003

Data Index: 995099 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1303355 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1301267 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1275088 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0606. Min Act: -0.0003

Data Index: 986152 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1214733 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0605. Min Act: -0.0003

Data Index: 967876 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1140253 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0591. Min Act: -0.0003

Data Index: 470581 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0575. Min Act: -0.0003

Data Index: 96507 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0558. Min Act: -0.0003

Data Index: 725289 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0597. Min Act: -0.0003

Data Index: 21076 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0579. Min Act: -0.0003

Data Index: 425874 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0596. Min Act: -0.0003

Data Index: 611368 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0561. Min Act: -0.0003

Data Index: 427049 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1070810 (C4 (Web Text))

Max Activating Token Index: 419