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

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

Neuron 5493 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: 3.2355. Min Range: -3.2355

Max Act: 3.2355. Min Act: -0.0000

Data Index: 612236 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.9646. Min Act: -0.0001

Data Index: 651269 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.4465. Min Act: -0.0001

Data Index: 760983 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.4804. Min Act: -0.0000

Data Index: 1269990 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.4912. Min Act: -0.0001

Data Index: 879936 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.3625. Min Act: -0.0001

Data Index: 1115806 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.3433. Min Act: -0.0000

Data Index: 896417 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.0194. Min Act: -0.0001

Data Index: 56534 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.3594. Min Act: -0.0001

Data Index: 510030 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.2355. Min Range: -3.2355

Max Act: 1.8753. Min Act: -0.0000

Data Index: 372274 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.2362. Min Act: -0.0000

Data Index: 202009 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.1167. Min Act: -0.0001

Data Index: 255891 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.2067. Min Act: -0.0000

Data Index: 437663 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 3.2355. Min Range: -3.2355

Max Act: 1.8122. Min Act: -0.0000

Data Index: 584142 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.0848. Min Act: -0.0000

Data Index: 333742 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.1725. Min Act: -0.0001

Data Index: 129873 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.0721. Min Act: -0.0000

Data Index: 704323 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.0736. Min Act: -0.0001

Data Index: 212182 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1035219 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 3.2355. Min Range: -3.2355

Max Act: 2.3830. Min Act: -0.0000

Data Index: 304020 (C4 (Web Text))

Max Activating Token Index: 625