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

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

Neuron 3836 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0919. Min Act: -0.0001

Data Index: 275357 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1202918 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0650. Min Act: -0.0001

Data Index: 501938 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1388686 (Python Code)

Max Activating Token Index: 704

Text #4

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1129279 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0607. Min Act: -0.0001

Data Index: 801878 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0629. Min Act: -0.0001

Data Index: 452472 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0619. Min Act: -0.0001

Data Index: 877316 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1135673 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0611. Min Act: -0.0001

Data Index: 307194 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1592612 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0599. Min Act: -0.0001

Data Index: 631457 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1645193 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0591. Min Act: -0.0001

Data Index: 826913 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1112557 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1637787 (Python Code)

Max Activating Token Index: 691

Text #16

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0572. Min Act: -0.0001

Data Index: 60093 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0555. Min Act: -0.0001

Data Index: 402424 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0540. Min Act: -0.0001

Data Index: 27034 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.0919. Min Range: -0.0919

Max Act: 0.0578. Min Act: -0.0001

Data Index: 313548 (C4 (Web Text))

Max Activating Token Index: 458