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

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

Neuron 215 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: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1412873 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1451698 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1403981 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1533105 (Python Code)

Max Activating Token Index: 373

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0536. Min Act: -0.0002

Data Index: 753182 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1362283 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1647042 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1369631 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1452465 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1412454 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0483. Min Act: -0.0002

Data Index: 414093 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1656300 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1647105 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1433849 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1530180 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0483. Min Act: -0.0002

Data Index: 943436 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1551190 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1392084 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1561678 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1143044 (C4 (Web Text))

Max Activating Token Index: 840