Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.5966. Min Act: -0.0001

Data Index: 553716 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4483. Min Act: -0.0002

Data Index: 54687 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4744. Min Act: -0.0002

Data Index: 734406 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4273. Min Act: -0.0002

Data Index: 438824 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4638. Min Act: -0.0001

Data Index: 85335 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4322. Min Act: -0.0002

Data Index: 291627 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4180. Min Act: -0.0002

Data Index: 1088673 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4649. Min Act: -0.0002

Data Index: 1153177 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4331. Min Act: -0.0002

Data Index: 387255 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4059. Min Act: -0.0001

Data Index: 982242 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4615. Min Act: -0.0002

Data Index: 1140615 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3990. Min Act: -0.0002

Data Index: 1349275 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4125. Min Act: -0.0002

Data Index: 405733 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4044. Min Act: -0.0002

Data Index: 692033 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3836. Min Act: -0.0002

Data Index: 970097 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3704. Min Act: -0.0002

Data Index: 229646 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3368. Min Act: -0.0002

Data Index: 361857 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3323. Min Act: -0.0002

Data Index: 602364 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3998. Min Act: -0.0002

Data Index: 1234263 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3496. Min Act: -0.0001

Data Index: 162400 (C4 (Web Text))

Max Activating Token Index: 546