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

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

Neuron 4619 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: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0002

Data Index: 55126 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1026103 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1345514 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0665. Min Act: -0.0002

Data Index: 667227 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0612. Min Act: -0.0002

Data Index: 763967 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0654. Min Act: -0.0002

Data Index: 213663 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1125673 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0615. Min Act: -0.0002

Data Index: 122765 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0622. Min Act: -0.0002

Data Index: 385634 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0613. Min Act: -0.0002

Data Index: 551633 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0603. Min Act: -0.0002

Data Index: 540710 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1151312 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0664. Min Act: -0.0002

Data Index: 866045 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1092977 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0572. Min Act: -0.0002

Data Index: 464766 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0616. Min Act: -0.0002

Data Index: 227796 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0542. Min Act: -0.0002

Data Index: 283264 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0549. Min Act: -0.0002

Data Index: 682151 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0589. Min Act: -0.0002

Data Index: 278929 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0584. Min Act: -0.0002

Data Index: 962315 (C4 (Web Text))

Max Activating Token Index: 74