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

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

Neuron 1018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.6553. Min Act: -0.0000

Data Index: 961203 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5936. Min Act: -0.0000

Data Index: 295044 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5553. Min Act: -0.0000

Data Index: 452907 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5530. Min Act: -0.0000

Data Index: 399559 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1521893 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1608426 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5371. Min Act: -0.0000

Data Index: 5964 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1573678 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1336879 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1522443 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1042373 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1513921 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1379544 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5111. Min Act: -0.0000

Data Index: 895150 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1438523 (Python Code)

Max Activating Token Index: 721

Text #15

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1091333 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1469977 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4745. Min Act: -0.0000

Data Index: 678445 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1448252 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 0.6553. Min Range: -0.6553

Max Act: 0.4413. Min Act: -0.0000

Data Index: 14370 (C4 (Web Text))

Max Activating Token Index: 263