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

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

Neuron 498 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4270. Min Act: -0.0000

Data Index: 628366 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.4366. Min Act: -0.0000

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1326395 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1514156 (Python Code)

Max Activating Token Index: 422

Text #7

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3395. Min Act: -0.0000

Data Index: 104311 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1595130 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1442774 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1195216 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1316450 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3381. Min Act: -0.0000

Data Index: 651857 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.3087. Min Act: -0.0000

Data Index: 722817 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1340019 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2994. Min Act: -0.0000

Data Index: 694264 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2856. Min Act: -0.0000

Data Index: 185588 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1434773 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2833. Min Act: -0.0000

Data Index: 712339 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.4366. Min Range: -0.4366

Max Act: 0.2860. Min Act: -0.0000

Data Index: 945181 (C4 (Web Text))

Max Activating Token Index: 879