Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0566. Min Range: -1.0566

Max Act: 1.0566. Min Act: -0.0000

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.9331. Min Act: -0.0001

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.9646. Min Act: -0.0001

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.9642. Min Act: -0.0001

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.9191. Min Act: -0.0001

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.6704. Min Act: -0.0000

Data Index: 133034 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1364824 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.9334. Min Act: -0.0001

Data Index: 659418 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7249. Min Act: -0.0000

Data Index: 898699 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1486567 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1443380 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7879. Min Act: -0.0001

Data Index: 58551 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1466819 (Python Code)

Max Activating Token Index: 811

Text #13

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1547865 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1583012 (Python Code)

Max Activating Token Index: 955

Text #15

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1556534 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7310. Min Act: -0.0001

Data Index: 1466164 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1440304 (Python Code)

Max Activating Token Index: 662

Text #18

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1567218 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 1.0566. Min Range: -1.0566

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1571365 (Python Code)

Max Activating Token Index: 799