Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0002

Data Index: 520389 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0538. Min Act: -0.0002

Data Index: 985507 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1130156 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0455. Min Act: -0.0002

Data Index: 122949 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0458. Min Act: -0.0002

Data Index: 322212 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1061937 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0462. Min Act: -0.0002

Data Index: 144946 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0455. Min Act: -0.0002

Data Index: 423231 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0443. Min Act: -0.0002

Data Index: 304564 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0435. Min Act: -0.0002

Data Index: 915265 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0441. Min Act: -0.0002

Data Index: 400945 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0434. Min Act: -0.0002

Data Index: 328103 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0452. Min Act: -0.0002

Data Index: 556534 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0429. Min Act: -0.0002

Data Index: 907759 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0430. Min Act: -0.0002

Data Index: 148960 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1064406 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0419. Min Act: -0.0002

Data Index: 898124 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0412. Min Act: -0.0002

Data Index: 896206 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1356430 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0390. Min Act: -0.0002

Data Index: 795742 (C4 (Web Text))

Max Activating Token Index: 835