Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 33 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0751. Min Act: -0.0002

Data Index: 530824 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1138970 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0724. Min Act: -0.0002

Data Index: 694146 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0002

Data Index: 217555 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1293441 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0675. Min Act: -0.0002

Data Index: 849927 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1009600 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0701. Min Act: -0.0002

Data Index: 703356 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0704. Min Act: -0.0002

Data Index: 117338 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0664. Min Act: -0.0002

Data Index: 109385 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0680. Min Act: -0.0002

Data Index: 302766 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1217057 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1047363 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0702. Min Act: -0.0002

Data Index: 225167 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0647. Min Act: -0.0002

Data Index: 584247 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0653. Min Act: -0.0002

Data Index: 991342 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0609. Min Act: -0.0002

Data Index: 353080 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0665. Min Act: -0.0002

Data Index: 608134 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0627. Min Act: -0.0002

Data Index: 313331 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0630. Min Act: -0.0002

Data Index: 326082 (C4 (Web Text))

Max Activating Token Index: 364