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

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

Neuron 28 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0003

Data Index: 144050 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0785. Min Act: -0.0004

Data Index: 394227 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0813. Min Act: -0.0003

Data Index: 1232063 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0793. Min Act: -0.0004

Data Index: 1182514 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0789. Min Act: -0.0003

Data Index: 956602 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0750. Min Act: -0.0003

Data Index: 471856 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0723. Min Act: -0.0003

Data Index: 916113 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0737. Min Act: -0.0003

Data Index: 390250 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0762. Min Act: -0.0003

Data Index: 454791 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0734. Min Act: -0.0003

Data Index: 831516 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0729. Min Act: -0.0003

Data Index: 282314 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0716. Min Act: -0.0003

Data Index: 393909 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0661. Min Act: -0.0003

Data Index: 311686 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1348531 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0683. Min Act: -0.0003

Data Index: 763653 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0682. Min Act: -0.0003

Data Index: 476485 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0703. Min Act: -0.0004

Data Index: 892117 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0701. Min Act: -0.0003

Data Index: 213350 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0692. Min Act: -0.0003

Data Index: 277413 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1206040 (C4 (Web Text))

Max Activating Token Index: 62