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

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

Neuron 3713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0002

Data Index: 909704 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0648. Min Act: -0.0002

Data Index: 57265 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0636. Min Act: -0.0002

Data Index: 68188 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0627. Min Act: -0.0002

Data Index: 53949 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0625. Min Act: -0.0003

Data Index: 917173 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0594. Min Act: -0.0002

Data Index: 928429 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0597. Min Act: -0.0002

Data Index: 304445 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0586. Min Act: -0.0002

Data Index: 18742 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0580. Min Act: -0.0002

Data Index: 55192 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0574. Min Act: -0.0002

Data Index: 780806 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0570. Min Act: -0.0002

Data Index: 588667 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1358397 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0566. Min Act: -0.0002

Data Index: 820782 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1127156 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0564. Min Act: -0.0002

Data Index: 837286 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0564. Min Act: -0.0002

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0570. Min Act: -0.0002

Data Index: 479593 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1240009 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0559. Min Act: -0.0002

Data Index: 877056 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0561. Min Act: -0.0002

Data Index: 710014 (C4 (Web Text))

Max Activating Token Index: 915