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

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

Neuron 4123 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: 0.5852. Min Range: -0.5852

Max Act: 0.5852. Min Act: -0.0000

Data Index: 688399 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.5623. Min Act: -0.0000

Data Index: 389038 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.5002. Min Act: -0.0000

Data Index: 428289 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.5028. Min Act: -0.0000

Data Index: 479516 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4440. Min Act: -0.0000

Data Index: 930507 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4703. Min Act: -0.0000

Data Index: 381600 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4813. Min Act: -0.0000

Data Index: 117738 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4534. Min Act: -0.0000

Data Index: 781898 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4157. Min Act: -0.0000

Data Index: 631207 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1176132 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.4210. Min Act: -0.0000

Data Index: 932765 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3974. Min Act: -0.0000

Data Index: 853110 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3986. Min Act: -0.0000

Data Index: 522443 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3799. Min Act: -0.0000

Data Index: 669357 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1199017 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3594. Min Act: -0.0000

Data Index: 13234 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3612. Min Act: -0.0000

Data Index: 523435 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3783. Min Act: -0.0000

Data Index: 592258 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3689. Min Act: -0.0000

Data Index: 833761 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.5852. Min Range: -0.5852

Max Act: 0.3665. Min Act: -0.0000

Data Index: 673176 (C4 (Web Text))

Max Activating Token Index: 837