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

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

Neuron 1820 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0286. Min Range: -2.0286

Max Act: 2.0286. Min Act: -0.0000

Data Index: 857075 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.7621. Min Act: -0.0000

Data Index: 591661 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.4334. Min Act: -0.0000

Data Index: 129100 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.3092. Min Act: -0.0000

Data Index: 213008 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.2672. Min Act: -0.0000

Data Index: 339531 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.3601. Min Act: -0.0000

Data Index: 401773 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.2216. Min Act: -0.0000

Data Index: 142002 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1901. Min Act: -0.0000

Data Index: 1349027 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1213. Min Act: -0.0000

Data Index: 276911 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1577. Min Act: -0.0000

Data Index: 978768 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1324. Min Act: 0.0000

Data Index: 929419 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 2.0286. Min Range: -2.0286

Max Act: 0.9971. Min Act: -0.0000

Data Index: 63460 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.0285. Min Act: -0.0000

Data Index: 151077 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1430. Min Act: -0.0000

Data Index: 929106 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.1346. Min Act: -0.0000

Data Index: 584697 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.0749. Min Act: -0.0000

Data Index: 928419 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 2.0286. Min Range: -2.0286

Max Act: 1.0936. Min Act: -0.0000

Data Index: 661713 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 2.0286. Min Range: -2.0286

Max Act: 0.9762. Min Act: -0.0000

Data Index: 815252 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 2.0286. Min Range: -2.0286

Max Act: 0.9768. Min Act: -0.0000

Data Index: 285770 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 2.0286. Min Range: -2.0286

Max Act: 0.9041. Min Act: -0.0000

Data Index: 116249 (C4 (Web Text))

Max Activating Token Index: 336