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

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

Neuron 3872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0000

Data Index: 590694 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0715. Min Act: -0.0000

Data Index: 734558 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0698. Min Act: -0.0000

Data Index: 80435 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0694. Min Act: -0.0000

Data Index: 820072 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1209139 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1304818 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0609. Min Act: -0.0000

Data Index: 271974 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1206468 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1006849 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0588. Min Act: -0.0000

Data Index: 396880 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0539. Min Act: -0.0000

Data Index: 378672 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1155989 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1168171 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0574. Min Act: -0.0000

Data Index: 233041 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0543. Min Act: -0.0000

Data Index: 397419 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0534. Min Act: -0.0000

Data Index: 140154 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1171039 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0558. Min Act: -0.0000

Data Index: 602327 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0520. Min Act: -0.0000

Data Index: 109791 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0496. Min Act: -0.0000

Data Index: 343113 (C4 (Web Text))

Max Activating Token Index: 810