Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0777. Min Act: -0.0002

Data Index: 293153 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1063643 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0761. Min Act: -0.0001

Data Index: 961276 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0695. Min Act: -0.0002

Data Index: 768411 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0671. Min Act: -0.0001

Data Index: 981504 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0720. Min Act: -0.0002

Data Index: 572948 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1246472 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0610. Min Act: -0.0002

Data Index: 86301 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1286982 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0644. Min Act: -0.0002

Data Index: 752257 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0651. Min Act: -0.0002

Data Index: 876416 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0570. Min Act: -0.0002

Data Index: 380936 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0617. Min Act: -0.0001

Data Index: 971487 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0560. Min Act: -0.0002

Data Index: 849880 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1131643 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0553. Min Act: -0.0002

Data Index: 712311 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1164469 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1025242 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0590. Min Act: -0.0002

Data Index: 319284 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1116225 (C4 (Web Text))

Max Activating Token Index: 370