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

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

Neuron 1728 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: 1.6833. Min Range: -1.6833

Max Act: 1.6833. Min Act: -0.0001

Data Index: 1141557 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.5769. Min Act: -0.0001

Data Index: 1054376 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.5298. Min Act: -0.0001

Data Index: 402551 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.4372. Min Act: -0.0001

Data Index: 389986 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.4085. Min Act: -0.0001

Data Index: 972017 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.3949. Min Act: -0.0001

Data Index: 961614 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.3333. Min Act: -0.0001

Data Index: 703728 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.3261. Min Act: -0.0001

Data Index: 1022268 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.3378. Min Act: -0.0001

Data Index: 672175 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.1861. Min Act: -0.0001

Data Index: 1086133 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2223. Min Act: -0.0000

Data Index: 639424 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2782. Min Act: -0.0001

Data Index: 91025 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.1838. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2545. Min Act: -0.0000

Data Index: 152900 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2533. Min Act: -0.0000

Data Index: 329415 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2059. Min Act: -0.0001

Data Index: 18647 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.1810. Min Act: -0.0001

Data Index: 1030477 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.2195. Min Act: -0.0001

Data Index: 1118747 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.0984. Min Act: -0.0001

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 1.6833. Min Range: -1.6833

Max Act: 1.1765. Min Act: -0.0001

Data Index: 343792 (C4 (Web Text))

Max Activating Token Index: 719