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

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

Neuron 91 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: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1011262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0782. Min Act: -0.0002

Data Index: 31421 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0736. Min Act: -0.0002

Data Index: 537268 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1251436 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0735. Min Act: -0.0002

Data Index: 53671 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0714. Min Act: -0.0002

Data Index: 114948 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1214965 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0694. Min Act: -0.0002

Data Index: 703497 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0705. Min Act: -0.0002

Data Index: 752693 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1014561 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0713. Min Act: -0.0002

Data Index: 958033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1063407 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1133883 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0703. Min Act: -0.0002

Data Index: 322676 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0700. Min Act: -0.0002

Data Index: 652170 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0672. Min Act: -0.0002

Data Index: 543252 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0706. Min Act: -0.0002

Data Index: 798122 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0672. Min Act: -0.0002

Data Index: 252248 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1301230 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0678. Min Act: -0.0002

Data Index: 656183 (C4 (Web Text))

Max Activating Token Index: 567