Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0002

Data Index: 35613 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0778. Min Act: -0.0002

Data Index: 411257 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0717. Min Act: -0.0002

Data Index: 349856 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1447813 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1295565 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0718. Min Act: -0.0002

Data Index: 869421 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0702. Min Act: -0.0002

Data Index: 953049 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0665. Min Act: -0.0002

Data Index: 774416 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0691. Min Act: -0.0002

Data Index: 685397 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1504471 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0634. Min Act: -0.0002

Data Index: 116305 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0655. Min Act: -0.0002

Data Index: 184628 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0636. Min Act: -0.0002

Data Index: 963082 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1501950 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1005491 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0626. Min Act: -0.0002

Data Index: 364717 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0644. Min Act: -0.0002

Data Index: 177727 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1109771 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0593. Min Act: -0.0002

Data Index: 753285 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1289354 (C4 (Web Text))

Max Activating Token Index: 94