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

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

Neuron 1625 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1475956 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1466640 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5913. Min Act: -0.0000

Data Index: 455262 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1555436 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1429350 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1456795 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1375862 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4006. Min Act: -0.0000

Data Index: 349695 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1331714 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3988. Min Act: -0.0000

Data Index: 691137 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1401703 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1627781 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3757. Min Act: -0.0000

Data Index: 720794 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3707. Min Act: -0.0000

Data Index: 224135 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1395560 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1549932 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1423061 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3744. Min Act: 0.0000

Data Index: 949571 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1643215 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.3555. Min Act: 0.0000

Data Index: 32106 (C4 (Web Text))

Max Activating Token Index: 496