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

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

Neuron 3770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5466. Min Act: -0.0000

Data Index: 1210845 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.6017. Min Act: -0.0000

Data Index: 338109 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.3101. Min Act: -0.0000

Data Index: 838018 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9824. Min Act: -0.0000

Data Index: 1076772 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.8335. Min Act: -0.0000

Data Index: 1183393 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.7394. Min Act: -0.0000

Data Index: 1173565 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9839. Min Act: -0.0000

Data Index: 1165804 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9488. Min Act: -0.0000

Data Index: 1003405 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.4875. Min Act: -0.0000

Data Index: 773318 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9485. Min Act: -0.0000

Data Index: 299525 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9218. Min Act: -0.0000

Data Index: 490647 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.7643. Min Act: -0.0000

Data Index: 794744 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.7675. Min Act: -0.0000

Data Index: 513039 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.5145. Min Act: -0.0000

Data Index: 136934 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.7904. Min Act: -0.0000

Data Index: 65553 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.0378. Min Act: -0.0000

Data Index: 1078650 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.7458. Min Act: -0.0000

Data Index: 270650 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.8669. Min Act: -0.0000

Data Index: 767527 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.8427. Min Act: -0.0000

Data Index: 145083 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.6017. Min Range: -3.6017

Max Act: 2.9180. Min Act: -0.0000

Data Index: 846728 (C4 (Web Text))

Max Activating Token Index: 942