Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4771 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1284362 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1538026 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0715. Min Act: -0.0002

Data Index: 962691 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1414765 (Python Code)

Max Activating Token Index: 862

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1528481 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1387614 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1370137 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0661. Min Act: -0.0002

Data Index: 483819 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1276643 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1469889 (Python Code)

Max Activating Token Index: 584

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0646. Min Act: -0.0002

Data Index: 453187 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1655310 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1482752 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0619. Min Act: -0.0002

Data Index: 852344 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1378910 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0617. Min Act: -0.0002

Data Index: 906466 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1552446 (Python Code)

Max Activating Token Index: 148

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1584355 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1593734 (Python Code)

Max Activating Token Index: 359