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

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

Neuron 1964 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: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1398404 (Python Code)

Max Activating Token Index: 944

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0506. Min Act: -0.0002

Data Index: 622388 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1517710 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1633847 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0492. Min Act: -0.0002

Data Index: 101653 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1529245 (Python Code)

Max Activating Token Index: 506

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0501. Min Act: -0.0002

Data Index: 353837 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1480487 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0460. Min Act: -0.0002

Data Index: 25853 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1533524 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0432. Min Act: -0.0002

Data Index: 231319 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0509. Min Act: -0.0002

Data Index: 681067 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1588687 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1430564 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0449. Min Act: -0.0002

Data Index: 796478 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0442. Min Act: -0.0002

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0459. Min Act: -0.0002

Data Index: 821164 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0451. Min Act: -0.0002

Data Index: 468693 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1245044 (C4 (Web Text))

Max Activating Token Index: 143