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

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

Neuron 1364 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: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1105228 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0837. Min Act: -0.0001

Data Index: 725814 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1032960 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0709. Min Act: -0.0001

Data Index: 492262 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1305546 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0616. Min Act: -0.0002

Data Index: 470092 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0723. Min Act: -0.0002

Data Index: 761107 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0810. Min Act: -0.0001

Data Index: 330485 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0713. Min Act: -0.0002

Data Index: 141742 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0685. Min Act: -0.0002

Data Index: 418966 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0677. Min Act: -0.0001

Data Index: 82995 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0699. Min Act: -0.0002

Data Index: 168589 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1327574 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0717. Min Act: -0.0001

Data Index: 6817 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1245655 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1328758 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0645. Min Act: -0.0001

Data Index: 301126 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0662. Min Act: -0.0002

Data Index: 505781 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0685. Min Act: -0.0001

Data Index: 229601 (C4 (Web Text))

Max Activating Token Index: 473