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

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

Neuron 667 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: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0001

Data Index: 276871 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0727. Min Act: -0.0003

Data Index: 491775 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0741. Min Act: -0.0003

Data Index: 85250 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0725. Min Act: -0.0003

Data Index: 251806 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0700. Min Act: -0.0003

Data Index: 297180 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1163051 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0664. Min Act: -0.0003

Data Index: 319097 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1252359 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1165026 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0643. Min Act: -0.0003

Data Index: 339866 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0641. Min Act: -0.0001

Data Index: 157255 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0617. Min Act: -0.0001

Data Index: 739143 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0648. Min Act: -0.0003

Data Index: 720995 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0623. Min Act: -0.0004

Data Index: 99604 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0641. Min Act: -0.0002

Data Index: 397849 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0636. Min Act: -0.0003

Data Index: 382249 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0633. Min Act: -0.0003

Data Index: 544082 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0630. Min Act: -0.0003

Data Index: 361535 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0633. Min Act: -0.0002

Data Index: 909343 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0626. Min Act: -0.0003

Data Index: 338982 (C4 (Web Text))

Max Activating Token Index: 95