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

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

Neuron 457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.4564. Min Act: -0.0001

Data Index: 100763 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.3729. Min Act: -0.0001

Data Index: 902581 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.4316. Min Act: -0.0001

Data Index: 168016 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.3011. Min Act: -0.0001

Data Index: 554622 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1120. Min Act: -0.0001

Data Index: 973911 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2783. Min Act: -0.0001

Data Index: 1085948 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2880. Min Act: -0.0001

Data Index: 1556281 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2785. Min Act: -0.0001

Data Index: 1351552 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.0866. Min Act: -0.0001

Data Index: 560660 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1606. Min Act: -0.0001

Data Index: 1025675 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.0861. Min Act: -0.0001

Data Index: 896519 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2177. Min Act: -0.0001

Data Index: 694905 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1484. Min Act: -0.0001

Data Index: 494027 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2747. Min Act: -0.0000

Data Index: 549142 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2676. Min Act: -0.0001

Data Index: 289558 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2570. Min Act: -0.0001

Data Index: 852216 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1781. Min Act: -0.0001

Data Index: 378337 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.1758. Min Act: -0.0001

Data Index: 937455 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2347. Min Act: -0.0001

Data Index: 333742 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 1.4564. Min Range: -1.4564

Max Act: 1.2207. Min Act: -0.0001

Data Index: 1384686 (Python Code)

Max Activating Token Index: 435