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

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

Neuron 782 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: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1561989 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1631477 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0615. Min Act: -0.0004

Data Index: 689940 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1453445 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1563626 (Python Code)

Max Activating Token Index: 657

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1512364 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0563. Min Act: -0.0003

Data Index: 261822 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1625706 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1202292 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1260958 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1581192 (Python Code)

Max Activating Token Index: 335

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0537. Min Act: -0.0003

Data Index: 329655 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1615572 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1573614 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1496215 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1426265 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1565046 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1402604 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0532. Min Act: -0.0003

Data Index: 466311 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0521. Min Act: -0.0003

Data Index: 977116 (C4 (Web Text))

Max Activating Token Index: 12