Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 933 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0003

Data Index: 746794 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0928. Min Act: -0.0003

Data Index: 361721 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0808. Min Act: -0.0002

Data Index: 26175 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1258043 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0795. Min Act: -0.0003

Data Index: 641417 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0809. Min Act: -0.0002

Data Index: 532492 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0803. Min Act: -0.0003

Data Index: 774203 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1572876 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0766. Min Act: -0.0003

Data Index: 495249 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0772. Min Act: -0.0003

Data Index: 822651 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1117697 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1086344 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1377934 (Python Code)

Max Activating Token Index: 557

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1434263 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1383953 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0726. Min Act: -0.0003

Data Index: 1363443 (Python Code)

Max Activating Token Index: 694

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0725. Min Act: -0.0003

Data Index: 345702 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0715. Min Act: -0.0003

Data Index: 511742 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1316652 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0726. Min Act: -0.0003

Data Index: 468577 (C4 (Web Text))

Max Activating Token Index: 832