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

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

Neuron 119 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: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1281754 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0781. Min Act: -0.0002

Data Index: 289372 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0617. Min Act: -0.0002

Data Index: 870038 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1220082 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0673. Min Act: -0.0002

Data Index: 420486 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1506544 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0666. Min Act: -0.0002

Data Index: 651307 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1491540 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0662. Min Act: -0.0002

Data Index: 511830 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1089351 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0626. Min Act: -0.0002

Data Index: 136923 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0643. Min Act: -0.0002

Data Index: 32581 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1309939 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0693. Min Act: -0.0002

Data Index: 859858 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1254878 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1447813 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0589. Min Act: -0.0002

Data Index: 35115 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0565. Min Act: -0.0002

Data Index: 348514 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1109246 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0623. Min Act: -0.0002

Data Index: 663358 (C4 (Web Text))

Max Activating Token Index: 323