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

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

Neuron 595 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: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1314978 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0555. Min Act: -0.0002

Data Index: 673522 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0541. Min Act: -0.0002

Data Index: 707582 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0530. Min Act: -0.0002

Data Index: 595978 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0539. Min Act: -0.0001

Data Index: 818638 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0515. Min Act: -0.0002

Data Index: 979777 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0526. Min Act: -0.0002

Data Index: 145814 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0521. Min Act: -0.0002

Data Index: 229836 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0515. Min Act: -0.0002

Data Index: 498284 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1285120 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0479. Min Act: -0.0002

Data Index: 27888 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0500. Min Act: -0.0002

Data Index: 290310 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1326390 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1161539 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0496. Min Act: -0.0001

Data Index: 87148 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0488. Min Act: -0.0001

Data Index: 586321 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0478. Min Act: -0.0001

Data Index: 77008 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0512. Min Act: -0.0002

Data Index: 944624 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1027435 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0493. Min Act: -0.0002

Data Index: 891943 (C4 (Web Text))

Max Activating Token Index: 404