Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1883 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0003

Data Index: 519450 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0852. Min Act: -0.0004

Data Index: 1063023 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0801. Min Act: -0.0004

Data Index: 1313646 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0804. Min Act: -0.0003

Data Index: 804850 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0743. Min Act: -0.0004

Data Index: 1257867 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0723. Min Act: -0.0003

Data Index: 693168 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0719. Min Act: -0.0004

Data Index: 1223315 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0695. Min Act: -0.0004

Data Index: 1046097 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0673. Min Act: -0.0003

Data Index: 298607 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0675. Min Act: -0.0004

Data Index: 592320 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0658. Min Act: -0.0004

Data Index: 877784 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0662. Min Act: -0.0004

Data Index: 977576 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0656. Min Act: -0.0004

Data Index: 833134 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0665. Min Act: -0.0004

Data Index: 959922 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0646. Min Act: -0.0003

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0640. Min Act: -0.0004

Data Index: 146440 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0653. Min Act: -0.0004

Data Index: 470897 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0649. Min Act: -0.0004

Data Index: 159697 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0626. Min Act: -0.0004

Data Index: 1001984 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1354148 (C4 (Web Text))

Max Activating Token Index: 303