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

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

Neuron 2016 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: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0002

Data Index: 679174 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0556. Min Act: -0.0002

Data Index: 732199 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0602. Min Act: -0.0002

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1100272 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0527. Min Act: -0.0002

Data Index: 32949 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1042548 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0569. Min Act: -0.0002

Data Index: 778551 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0588. Min Act: -0.0002

Data Index: 204314 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0597. Min Act: -0.0002

Data Index: 522333 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0554. Min Act: -0.0002

Data Index: 923499 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0576. Min Act: -0.0002

Data Index: 155297 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1294554 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0487. Min Act: -0.0002

Data Index: 887926 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0580. Min Act: -0.0003

Data Index: 604579 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1282234 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0504. Min Act: -0.0002

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0513. Min Act: -0.0002

Data Index: 385719 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0530. Min Act: -0.0002

Data Index: 606892 (C4 (Web Text))

Max Activating Token Index: 718