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

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

Neuron 4706 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.5768. Min Act: -0.0000

Data Index: 146376 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1294361 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.2554. Min Act: -0.0000

Data Index: 634974 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1966. Min Act: -0.0000

Data Index: 447711 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.0653. Min Act: -0.0000

Data Index: 268124 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1076556 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8515. Min Act: -0.0000

Data Index: 1150112 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.0084. Min Act: -0.0000

Data Index: 1173126 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1303. Min Act: -0.0000

Data Index: 526139 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9782. Min Act: -0.0000

Data Index: 973033 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9357. Min Act: -0.0000

Data Index: 151393 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7291. Min Act: -0.0000

Data Index: 106439 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7877. Min Act: -0.0000

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9589. Min Act: -0.0000

Data Index: 1175427 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8143. Min Act: -0.0000

Data Index: 1246432 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1039801 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1278765 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1283841 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7898. Min Act: -0.0000

Data Index: 601848 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9012. Min Act: -0.0000

Data Index: 120667 (C4 (Web Text))

Max Activating Token Index: 993