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

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

Neuron 2821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0000

Data Index: 633451 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0908. Min Act: -0.0000

Data Index: 894873 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1153618 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1116403 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0867. Min Act: -0.0000

Data Index: 445087 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1352171 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0752. Min Act: -0.0000

Data Index: 89250 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0752. Min Act: -0.0000

Data Index: 856139 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1047659 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0746. Min Act: -0.0000

Data Index: 248056 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1607749 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1392076 (Python Code)

Max Activating Token Index: 679

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0657. Min Act: -0.0000

Data Index: 161603 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0694. Min Act: -0.0000

Data Index: 108708 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0653. Min Act: -0.0000

Data Index: 867182 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1534045 (Python Code)

Max Activating Token Index: 435

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0679. Min Act: -0.0000

Data Index: 132678 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1375971 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1046347 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0631. Min Act: -0.0000

Data Index: 517573 (C4 (Web Text))

Max Activating Token Index: 714