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

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

Neuron 295 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: 4.1307. Min Range: -4.1307

Max Act: 4.1307. Min Act: -0.0001

Data Index: 183582 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.8153. Min Act: -0.0000

Data Index: 489260 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.1455. Min Act: -0.0001

Data Index: 13331 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.1431. Min Act: -0.0000

Data Index: 908753 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.0512. Min Act: -0.0000

Data Index: 493784 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.6322. Min Act: -0.0000

Data Index: 961673 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.3924. Min Act: -0.0001

Data Index: 535487 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.0214. Min Act: -0.0001

Data Index: 1245274 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.0204. Min Act: -0.0000

Data Index: 721667 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.7737. Min Act: -0.0001

Data Index: 789940 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 4.1307. Min Range: -4.1307

Max Act: 3.1858. Min Act: -0.0001

Data Index: 1065221 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.7428. Min Act: -0.0000

Data Index: 622228 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.8640. Min Act: -0.0001

Data Index: 859494 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.7332. Min Act: -0.0001

Data Index: 1280393 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.6897. Min Act: -0.0000

Data Index: 979619 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.8928. Min Act: -0.0001

Data Index: 110951 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.5896. Min Act: -0.0001

Data Index: 933482 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.7107. Min Act: -0.0001

Data Index: 776677 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.6812. Min Act: -0.0000

Data Index: 31256 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 4.1307. Min Range: -4.1307

Max Act: 2.6741. Min Act: -0.0000

Data Index: 517524 (C4 (Web Text))

Max Activating Token Index: 391