Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.7220. Min Act: -0.0000

Data Index: 1525602 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.5668. Min Act: -0.0000

Data Index: 1605896 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.7597. Min Act: -0.0000

Data Index: 1367637 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.7613. Min Act: -0.0000

Data Index: 1377061 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1462072 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.3937. Min Act: -0.0000

Data Index: 1468742 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.2599. Min Act: -0.0000

Data Index: 1326628 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.2434. Min Act: -0.0000

Data Index: 479317 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.4860. Min Act: -0.0000

Data Index: 1619420 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.3502. Min Act: -0.0000

Data Index: 554535 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.0716. Min Act: -0.0000

Data Index: 852683 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.2928. Min Act: -0.0000

Data Index: 1633410 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.4091. Min Act: -0.0000

Data Index: 25090 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.1558. Min Act: -0.0000

Data Index: 1625000 (Python Code)

Max Activating Token Index: 583

Text #14

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.3466. Min Act: -0.0000

Data Index: 1570311 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.1129. Min Act: -0.0000

Data Index: 536841 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.1153. Min Act: -0.0000

Data Index: 1391309 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.0603. Min Act: -0.0000

Data Index: 284804 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.2635. Min Act: -0.0000

Data Index: 1441358 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 2.7613. Min Range: -2.7613

Max Act: 2.3717. Min Act: -0.0000

Data Index: 1465298 (Python Code)

Max Activating Token Index: 274