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

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

Neuron 5085 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1144487 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0001

Data Index: 863142 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1567122 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0637. Min Act: -0.0001

Data Index: 526937 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0621. Min Act: -0.0001

Data Index: 957843 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0621. Min Act: -0.0001

Data Index: 110049 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0599. Min Act: -0.0001

Data Index: 502980 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0551. Min Act: -0.0001

Data Index: 350713 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0577. Min Act: -0.0001

Data Index: 933885 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0597. Min Act: -0.0001

Data Index: 509707 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1283920 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1050857 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0578. Min Act: -0.0001

Data Index: 178134 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0528. Min Act: -0.0001

Data Index: 964687 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0528. Min Act: -0.0001

Data Index: 460087 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0531. Min Act: -0.0001

Data Index: 152510 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0508. Min Act: -0.0001

Data Index: 123189 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1362994 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1544971 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0522. Min Act: -0.0001

Data Index: 324674 (C4 (Web Text))

Max Activating Token Index: 208