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

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

Neuron 4161 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7297. Min Act: -0.0000

Data Index: 284428 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7675. Min Act: -0.0001

Data Index: 495462 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1097657 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6738. Min Act: -0.0000

Data Index: 417680 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6791. Min Act: -0.0000

Data Index: 565453 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1147142 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6194. Min Act: -0.0000

Data Index: 984149 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6371. Min Act: -0.0000

Data Index: 936751 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5720. Min Act: -0.0000

Data Index: 932640 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5795. Min Act: -0.0001

Data Index: 1015697 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1520181 (Python Code)

Max Activating Token Index: 944

Text #11

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5786. Min Act: -0.0000

Data Index: 655343 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1366114 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5710. Min Act: -0.0001

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5862. Min Act: -0.0000

Data Index: 359771 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1446354 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5615. Min Act: -0.0000

Data Index: 456048 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5379. Min Act: -0.0000

Data Index: 778917 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1542186 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5441. Min Act: -0.0000

Data Index: 347642 (C4 (Web Text))

Max Activating Token Index: 547