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

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

Neuron 435 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: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 189589 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1014. Min Act: -0.0001

Data Index: 716834 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1103. Min Act: -0.0001

Data Index: 318796 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0936. Min Act: -0.0001

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0944. Min Act: -0.0001

Data Index: 733583 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0958. Min Act: -0.0001

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0893. Min Act: -0.0001

Data Index: 615346 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0848. Min Act: -0.0001

Data Index: 940426 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1846 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0850. Min Act: -0.0001

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0907. Min Act: -0.0001

Data Index: 132405 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1075731 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0854. Min Act: -0.0001

Data Index: 512510 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0796. Min Act: -0.0001

Data Index: 784404 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0787. Min Act: -0.0001

Data Index: 217683 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0820. Min Act: -0.0001

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1920 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0835. Min Act: -0.0001

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0722. Min Act: -0.0001

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 670