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

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

Neuron 2022 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: 0.0710. Min Range: -0.0710

Max Act: 0.0708. Min Act: -0.0002

Data Index: 163737 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0002

Data Index: 580780 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0691. Min Act: -0.0002

Data Index: 139582 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0700. Min Act: -0.0002

Data Index: 933299 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0673. Min Act: -0.0002

Data Index: 280337 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1268713 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0630. Min Act: -0.0002

Data Index: 596861 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0681. Min Act: -0.0002

Data Index: 109810 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1298782 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1266524 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0661. Min Act: -0.0002

Data Index: 54765 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1105531 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0647. Min Act: -0.0002

Data Index: 155641 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0635. Min Act: -0.0002

Data Index: 847987 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0642. Min Act: -0.0002

Data Index: 640490 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0637. Min Act: -0.0002

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0607. Min Act: -0.0002

Data Index: 460336 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0647. Min Act: -0.0002

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0638. Min Act: -0.0002

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0614. Min Act: -0.0002

Data Index: 301759 (C4 (Web Text))

Max Activating Token Index: 145