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

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

Neuron 1947 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: 0.4976. Min Range: -0.4976

Max Act: 0.4976. Min Act: -0.0001

Data Index: 403680 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1312365 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4838. Min Act: -0.0001

Data Index: 1266984 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4738. Min Act: -0.0001

Data Index: 179750 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4752. Min Act: -0.0001

Data Index: 993085 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4710. Min Act: -0.0001

Data Index: 107869 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1649892 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1244576 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4690. Min Act: -0.0001

Data Index: 1512739 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1331616 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4707. Min Act: -0.0001

Data Index: 733749 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4568. Min Act: -0.0001

Data Index: 245878 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4539. Min Act: -0.0001

Data Index: 349134 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4634. Min Act: -0.0001

Data Index: 492757 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4570. Min Act: -0.0001

Data Index: 86990 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4631. Min Act: -0.0001

Data Index: 96825 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4511. Min Act: -0.0001

Data Index: 1140433 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4387. Min Act: -0.0001

Data Index: 776665 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4569. Min Act: -0.0001

Data Index: 296367 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4568. Min Act: -0.0001

Data Index: 682641 (C4 (Web Text))

Max Activating Token Index: 645