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

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

Neuron 3362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1014382 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9605. Min Act: -0.0000

Data Index: 927673 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8739. Min Act: -0.0000

Data Index: 831505 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7695. Min Act: -0.0000

Data Index: 391239 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1019721 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7555. Min Act: -0.0000

Data Index: 458753 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7736. Min Act: -0.0001

Data Index: 38213 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6704. Min Act: -0.0000

Data Index: 312889 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6652. Min Act: -0.0000

Data Index: 708253 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7099. Min Act: -0.0000

Data Index: 507785 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6602. Min Act: -0.0000

Data Index: 738535 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7186. Min Act: -0.0000

Data Index: 688701 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1189156 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7011. Min Act: -0.0000

Data Index: 340436 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6637. Min Act: -0.0000

Data Index: 448497 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1246831 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6230. Min Act: -0.0000

Data Index: 534417 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6415. Min Act: -0.0001

Data Index: 372577 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6756. Min Act: -0.0001

Data Index: 918698 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.6518. Min Act: -0.0000

Data Index: 287344 (C4 (Web Text))

Max Activating Token Index: 667