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

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

Neuron 768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0000

Data Index: 461430 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1528588 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0817. Min Act: -0.0000

Data Index: 854650 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0675. Min Act: -0.0000

Data Index: 683253 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0752. Min Act: -0.0000

Data Index: 81358 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0754. Min Act: -0.0000

Data Index: 323515 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0794. Min Act: -0.0000

Data Index: 619171 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0715. Min Act: -0.0000

Data Index: 866550 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0757. Min Act: -0.0000

Data Index: 280060 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0705. Min Act: -0.0000

Data Index: 175038 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0704. Min Act: -0.0000

Data Index: 190422 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0669. Min Act: -0.0000

Data Index: 146266 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0704. Min Act: -0.0000

Data Index: 209542 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1265608 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0612. Min Act: -0.0000

Data Index: 716889 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0609. Min Act: -0.0000

Data Index: 57349 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1042076 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1156742 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1160183 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0624. Min Act: -0.0000

Data Index: 189659 (C4 (Web Text))

Max Activating Token Index: 336