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

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

Neuron 3191 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0616. Min Range: -3.0616

Max Act: 3.0616. Min Act: -0.0000

Data Index: 1308463 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.0616. Min Range: -3.0616

Max Act: 2.1348. Min Act: -0.0000

Data Index: 118162 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 3.0616. Min Range: -3.0616

Max Act: 2.0948. Min Act: -0.0000

Data Index: 868198 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.9239. Min Act: -0.0000

Data Index: 356773 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1316982 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1095095 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.7473. Min Act: -0.0000

Data Index: 464747 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.7307. Min Act: -0.0000

Data Index: 996533 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.9163. Min Act: -0.0000

Data Index: 54230 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.7071. Min Act: -0.0000

Data Index: 853390 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.5603. Min Act: -0.0000

Data Index: 637013 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.6519. Min Act: 0.0000

Data Index: 986356 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.6489. Min Act: -0.0000

Data Index: 732299 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.7248. Min Act: -0.0000

Data Index: 732758 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.4838. Min Act: -0.0000

Data Index: 77469 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.5604. Min Act: -0.0000

Data Index: 264136 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.4850. Min Act: -0.0000

Data Index: 137666 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.6527. Min Act: -0.0000

Data Index: 65618 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.5518. Min Act: -0.0000

Data Index: 130513 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.0616. Min Range: -3.0616

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1138183 (C4 (Web Text))

Max Activating Token Index: 909