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

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

Neuron 303 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: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0002

Data Index: 892097 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0691. Min Act: -0.0002

Data Index: 645214 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0668. Min Act: -0.0002

Data Index: 367165 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0581. Min Act: -0.0002

Data Index: 94834 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0681. Min Act: -0.0002

Data Index: 69106 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0595. Min Act: -0.0002

Data Index: 331690 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1136491 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0575. Min Act: -0.0002

Data Index: 46296 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0532. Min Act: -0.0002

Data Index: 653303 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0570. Min Act: -0.0002

Data Index: 327444 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0568. Min Act: -0.0002

Data Index: 327541 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0606. Min Act: -0.0002

Data Index: 454525 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1190685 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1174358 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1041783 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0581. Min Act: -0.0002

Data Index: 148279 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0517. Min Act: -0.0002

Data Index: 901607 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0645. Min Act: -0.0002

Data Index: 893123 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1032351 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0502. Min Act: -0.0002

Data Index: 798094 (C4 (Web Text))

Max Activating Token Index: 46