Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0003

Data Index: 837089 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1369855 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1633719 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1382272 (Python Code)

Max Activating Token Index: 758

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1559036 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1552433 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1406873 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1607698 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1527654 (Python Code)

Max Activating Token Index: 415

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0631. Min Act: -0.0003

Data Index: 275952 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1631812 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1113068 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1495156 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1465341 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1292743 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0626. Min Act: -0.0003

Data Index: 197552 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0717. Min Act: -0.0003

Data Index: 271582 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1596157 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1600962 (Python Code)

Max Activating Token Index: 942

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1525550 (Python Code)

Max Activating Token Index: 659