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

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

Neuron 2514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: 0.0001

Data Index: 169398 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1004658 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6872. Min Act: -0.0000

Data Index: 337448 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6575. Min Act: -0.0000

Data Index: 6065 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1193359 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6462. Min Act: -0.0000

Data Index: 918499 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6656. Min Act: -0.0000

Data Index: 977588 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6648. Min Act: -0.0000

Data Index: 441050 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6181. Min Act: -0.0000

Data Index: 971202 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6542. Min Act: -0.0000

Data Index: 356342 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6506. Min Act: 0.0001

Data Index: 145613 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6148. Min Act: -0.0000

Data Index: 958410 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6262. Min Act: -0.0000

Data Index: 828815 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1290252 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5724. Min Act: -0.0000

Data Index: 838838 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5659. Min Act: 0.0001

Data Index: 368716 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5732. Min Act: -0.0000

Data Index: 132965 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1092793 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1231151 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1079420 (C4 (Web Text))

Max Activating Token Index: 471