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

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

Neuron 5810 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.7873. Min Act: -0.0000

Data Index: 1195569 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.3784. Min Act: -0.0000

Data Index: 604972 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.0779. Min Act: -0.0000

Data Index: 659236 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.7873. Min Range: -3.7873

Max Act: 3.0563. Min Act: -0.0000

Data Index: 765771 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.9725. Min Act: -0.0000

Data Index: 503640 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1199564 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.9579. Min Act: -0.0000

Data Index: 354550 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.6756. Min Act: -0.0000

Data Index: 867609 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.5951. Min Act: -0.0000

Data Index: 560751 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3549. Min Act: -0.0000

Data Index: 370581 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.7245. Min Act: -0.0000

Data Index: 378878 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3581. Min Act: -0.0000

Data Index: 1230806 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.5962. Min Act: -0.0000

Data Index: 876350 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1268764 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.6567. Min Act: -0.0000

Data Index: 484183 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.7873. Min Range: -3.7873

Max Act: 1.9539. Min Act: -0.0001

Data Index: 1155324 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.7693. Min Act: -0.0000

Data Index: 582999 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3687. Min Act: -0.0000

Data Index: 540189 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3443. Min Act: -0.0001

Data Index: 759957 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 3.7873. Min Range: -3.7873

Max Act: 2.3516. Min Act: -0.0000

Data Index: 563130 (C4 (Web Text))

Max Activating Token Index: 49