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

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

Neuron 3509 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0588. Min Act: -0.0001

Data Index: 29916 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0524. Min Act: -0.0001

Data Index: 498753 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0563. Min Act: -0.0001

Data Index: 83326 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0576. Min Act: -0.0001

Data Index: 707592 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0001

Data Index: 553789 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0579. Min Act: -0.0001

Data Index: 153904 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0518. Min Act: -0.0001

Data Index: 507668 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1214011 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0534. Min Act: -0.0001

Data Index: 643269 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0384. Min Act: -0.0001

Data Index: 78708 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1039803 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0441. Min Act: -0.0001

Data Index: 74685 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0462. Min Act: -0.0001

Data Index: 593449 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0538. Min Act: -0.0001

Data Index: 720884 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0399. Min Act: -0.0001

Data Index: 867646 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0452. Min Act: -0.0001

Data Index: 866061 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0389. Min Act: -0.0001

Data Index: 621185 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0503. Min Act: -0.0001

Data Index: 144395 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0498. Min Act: -0.0001

Data Index: 605790 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0503. Min Act: -0.0001

Data Index: 92483 (C4 (Web Text))

Max Activating Token Index: 756