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

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

Neuron 4657 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: 0.8014. Min Range: -0.8014

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1373766 (Python Code)

Max Activating Token Index: 677

Text #1

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.6234. Min Act: -0.0000

Data Index: 126926 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1569899 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1435666 (Python Code)

Max Activating Token Index: 196

Text #4

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5944. Min Act: -0.0000

Data Index: 999820 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5689. Min Act: -0.0000

Data Index: 156081 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5788. Min Act: -0.0000

Data Index: 681028 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5205. Min Act: -0.0000

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.5498. Min Act: -0.0000

Data Index: 406565 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1377864 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1309559 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1646649 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1553570 (Python Code)

Max Activating Token Index: 78

Text #13

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1524014 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4230. Min Act: -0.0000

Data Index: 774433 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1513073 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4550. Min Act: -0.0000

Data Index: 678925 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4573. Min Act: -0.0000

Data Index: 981800 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1552159 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.8014. Min Range: -0.8014

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1601548 (Python Code)

Max Activating Token Index: 352