Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4420. Min Act: -0.0001

Data Index: 400437 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4258. Min Act: -0.0001

Data Index: 1142908 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.4231. Min Act: -0.0001

Data Index: 998896 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3528. Min Act: -0.0001

Data Index: 780560 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3914. Min Act: -0.0001

Data Index: 656640 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3876. Min Act: -0.0001

Data Index: 500778 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1290352 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3751. Min Act: -0.0001

Data Index: 909683 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3729. Min Act: -0.0001

Data Index: 369520 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1112541 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3711. Min Act: -0.0001

Data Index: 495252 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3719. Min Act: -0.0001

Data Index: 762743 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3600. Min Act: -0.0001

Data Index: 618037 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1332702 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3563. Min Act: -0.0001

Data Index: 470426 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3547. Min Act: -0.0001

Data Index: 823427 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3753. Min Act: -0.0001

Data Index: 271188 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3652. Min Act: -0.0001

Data Index: 353969 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3621. Min Act: -0.0001

Data Index: 358809 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.4420. Min Range: -0.4420

Max Act: 0.3458. Min Act: -0.0001

Data Index: 840897 (C4 (Web Text))

Max Activating Token Index: 884