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

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

Neuron 4505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.4553. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0994. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0966. Min Act: -0.0000

Data Index: 357998 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1094948 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0857. Min Act: -0.0000

Data Index: 52438 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0910. Min Act: -0.0000

Data Index: 361841 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1160352 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0798. Min Act: -0.0000

Data Index: 172053 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0781. Min Act: -0.0000

Data Index: 165754 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0757. Min Act: -0.0000

Data Index: 43388 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0662. Min Act: -0.0000

Data Index: 402322 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1402908 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0673. Min Act: -0.0000

Data Index: 397204 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0706. Min Act: -0.0000

Data Index: 32668 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0424. Min Act: -0.0000

Data Index: 49585 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0634. Min Act: -0.0000

Data Index: 981730 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0601. Min Act: -0.0000

Data Index: 739368 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0601. Min Act: -0.0000

Data Index: 533419 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.5267. Min Range: -0.5267

Max Act: 0.0606. Min Act: -0.0000

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 713