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

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

Neuron 4373 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1049503 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6926. Min Act: -0.0000

Data Index: 310177 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6899. Min Act: -0.0000

Data Index: 176277 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6848. Min Act: -0.0000

Data Index: 104184 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1697 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6006. Min Act: -0.0000

Data Index: 234538 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1082189 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6473. Min Act: -0.0000

Data Index: 214892 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6532. Min Act: -0.0000

Data Index: 980642 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6778. Min Act: -0.0000

Data Index: 708452 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6023. Min Act: -0.0000

Data Index: 424726 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6232. Min Act: -0.0000

Data Index: 14754 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6342. Min Act: -0.0000

Data Index: 721484 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6315. Min Act: -0.0000

Data Index: 819451 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1181478 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6262. Min Act: -0.0000

Data Index: 427579 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6480. Min Act: -0.0000

Data Index: 824069 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5948. Min Act: -0.0000

Data Index: 933387 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5692. Min Act: -0.0000

Data Index: 480653 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5827. Min Act: -0.0000

Data Index: 934527 (C4 (Web Text))

Max Activating Token Index: 424