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

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

Neuron 3371 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0001

Data Index: 697511 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1010. Min Act: -0.0001

Data Index: 402554 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1278588 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1312683 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0968. Min Act: -0.0001

Data Index: 405900 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0781. Min Act: -0.0001

Data Index: 385820 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1238495 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1075424 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0844. Min Act: -0.0001

Data Index: 141852 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0782. Min Act: -0.0001

Data Index: 720479 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0730. Min Act: -0.0001

Data Index: 977691 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0770. Min Act: -0.0001

Data Index: 925100 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1206785 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1502405 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0789. Min Act: -0.0001

Data Index: 31380 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0762. Min Act: -0.0001

Data Index: 340064 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0782. Min Act: -0.0001

Data Index: 933461 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1078363 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0774. Min Act: -0.0001

Data Index: 650324 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0690. Min Act: -0.0001

Data Index: 866768 (C4 (Web Text))

Max Activating Token Index: 776