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

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

Neuron 4909 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.9512. Min Act: -0.0000

Data Index: 185963 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8999. Min Act: -0.0000

Data Index: 821650 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1087024 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8969. Min Act: -0.0000

Data Index: 588398 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1098460 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1313062 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.9194. Min Act: 0.0000

Data Index: 721788 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8354. Min Act: -0.0000

Data Index: 910834 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8476. Min Act: -0.0000

Data Index: 591985 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1007472 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8765. Min Act: -0.0000

Data Index: 798915 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8129. Min Act: -0.0000

Data Index: 624398 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8174. Min Act: -0.0000

Data Index: 505820 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8112. Min Act: -0.0000

Data Index: 324708 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7434. Min Act: -0.0000

Data Index: 175372 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1224175 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8604. Min Act: 0.0000

Data Index: 125930 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7931. Min Act: -0.0000

Data Index: 581471 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7909. Min Act: -0.0000

Data Index: 961640 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8385. Min Act: -0.0000

Data Index: 550287 (C4 (Web Text))

Max Activating Token Index: 487