Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0003

Data Index: 522524 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0532. Min Act: -0.0003

Data Index: 575628 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0517. Min Act: -0.0003

Data Index: 112636 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0519. Min Act: -0.0003

Data Index: 458528 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1024081 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0491. Min Act: -0.0003

Data Index: 910326 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0506. Min Act: -0.0003

Data Index: 886533 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0495. Min Act: -0.0003

Data Index: 782405 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1058999 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1055580 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1043837 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0496. Min Act: -0.0003

Data Index: 411489 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0492. Min Act: -0.0003

Data Index: 790342 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0473. Min Act: -0.0002

Data Index: 159187 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0468. Min Act: -0.0003

Data Index: 711188 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0478. Min Act: -0.0004

Data Index: 388391 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0484. Min Act: -0.0003

Data Index: 773008 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0475. Min Act: -0.0002

Data Index: 74167 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0474. Min Act: -0.0003

Data Index: 847827 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1093213 (C4 (Web Text))

Max Activating Token Index: 292