Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1109410 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1079743 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0482. Min Act: -0.0002

Data Index: 718857 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0447. Min Act: -0.0001

Data Index: 529752 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0426. Min Act: -0.0002

Data Index: 896521 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0396. Min Act: -0.0002

Data Index: 852134 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0413. Min Act: -0.0002

Data Index: 81783 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0397. Min Act: -0.0001

Data Index: 158234 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0378. Min Act: -0.0001

Data Index: 589567 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0394. Min Act: -0.0002

Data Index: 396891 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0377. Min Act: -0.0002

Data Index: 271333 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0387. Min Act: -0.0002

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0393. Min Act: -0.0002

Data Index: 227679 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1006985 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0394. Min Act: -0.0002

Data Index: 818647 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1155539 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1278054 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0365. Min Act: -0.0002

Data Index: 842656 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0002

Data Index: 764611 (C4 (Web Text))

Max Activating Token Index: 183