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

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

Neuron 334 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4573. Min Act: -0.0000

Data Index: 1267424 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2765. Min Act: -0.0000

Data Index: 472931 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.5698. Min Act: -0.0000

Data Index: 1105815 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.3932. Min Act: -0.0000

Data Index: 244897 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.4359. Min Act: -0.0000

Data Index: 875707 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.1490. Min Act: -0.0000

Data Index: 110766 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2857. Min Act: -0.0000

Data Index: 946419 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.1814. Min Act: -0.0000

Data Index: 120436 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.1014. Min Act: -0.0000

Data Index: 230242 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0782. Min Act: -0.0000

Data Index: 447756 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1169907 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0985. Min Act: -0.0000

Data Index: 477333 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1322161 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0930. Min Act: -0.0000

Data Index: 584960 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0235. Min Act: -0.0000

Data Index: 382678 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1161283 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1038895 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1071891 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.0110. Min Act: -0.0000

Data Index: 276631 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 1.5698. Min Range: -1.5698

Max Act: 1.2278. Min Act: -0.0000

Data Index: 78584 (C4 (Web Text))

Max Activating Token Index: 665