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

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

Neuron 679 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: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0002

Data Index: 442567 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0646. Min Act: -0.0002

Data Index: 211401 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1292659 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1301839 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1098821 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0643. Min Act: -0.0002

Data Index: 414472 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0588. Min Act: -0.0002

Data Index: 688347 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1325702 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1131910 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0536. Min Act: -0.0002

Data Index: 514786 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0542. Min Act: -0.0002

Data Index: 404608 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0540. Min Act: -0.0002

Data Index: 650908 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1573613 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0519. Min Act: -0.0002

Data Index: 239275 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0516. Min Act: -0.0002

Data Index: 564698 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0545. Min Act: -0.0002

Data Index: 260592 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0517. Min Act: -0.0002

Data Index: 564225 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0502. Min Act: -0.0002

Data Index: 473797 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0505. Min Act: -0.0002

Data Index: 722412 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1344473 (C4 (Web Text))

Max Activating Token Index: 681