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

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

Neuron 5603 in Layer 0

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: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1473639 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0789. Min Act: -0.0001

Data Index: 357842 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0787. Min Act: -0.0001

Data Index: 280429 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0784. Min Act: -0.0001

Data Index: 774400 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1646820 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0772. Min Act: -0.0001

Data Index: 688492 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1429174 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1504198 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1503472 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0769. Min Act: -0.0001

Data Index: 694243 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0763. Min Act: -0.0001

Data Index: 456562 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1226529 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1436453 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0752. Min Act: -0.0001

Data Index: 307306 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0770. Min Act: -0.0001

Data Index: 155188 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1062825 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0754. Min Act: -0.0001

Data Index: 765132 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1426891 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1553625 (Python Code)

Max Activating Token Index: 983

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1568271 (Python Code)

Max Activating Token Index: 881