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

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

Neuron 3882 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1385910 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1304481 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2021. Min Act: -0.0000

Data Index: 992331 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1995. Min Act: -0.0000

Data Index: 425459 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1801. Min Act: -0.0000

Data Index: 492637 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1749. Min Act: -0.0000

Data Index: 470590 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1612826 (Python Code)

Max Activating Token Index: 377

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1552. Min Act: -0.0000

Data Index: 815643 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1722. Min Act: -0.0000

Data Index: 364033 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1076400 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1239803 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1224287 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1830. Min Act: -0.0000

Data Index: 425981 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1611. Min Act: -0.0000

Data Index: 926809 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1113602 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1583. Min Act: -0.0000

Data Index: 940399 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1589. Min Act: -0.0000

Data Index: 265429 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1527. Min Act: -0.0000

Data Index: 160998 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1491520 (Python Code)

Max Activating Token Index: 905

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1216050 (C4 (Web Text))

Max Activating Token Index: 757