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

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

Neuron 1565 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: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0003

Data Index: 497877 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0732. Min Act: -0.0002

Data Index: 222539 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1140106 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0706. Min Act: -0.0003

Data Index: 700898 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1138540 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0680. Min Act: -0.0002

Data Index: 291904 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0686. Min Act: -0.0003

Data Index: 634864 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1013647 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0670. Min Act: -0.0003

Data Index: 465140 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0666. Min Act: -0.0003

Data Index: 509798 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0666. Min Act: -0.0003

Data Index: 897602 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0662. Min Act: -0.0003

Data Index: 215789 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1336802 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0640. Min Act: -0.0003

Data Index: 285718 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0637. Min Act: -0.0003

Data Index: 342211 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1253642 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0656. Min Act: -0.0003

Data Index: 124595 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0652. Min Act: -0.0003

Data Index: 527496 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0629. Min Act: -0.0003

Data Index: 39985 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0634. Min Act: -0.0002

Data Index: 220379 (C4 (Web Text))

Max Activating Token Index: 513