Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2981 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2514. Min Act: -0.0001

Data Index: 410242 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1066367 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2239. Min Act: -0.0001

Data Index: 694366 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1164361 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1334191 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1077576 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2163. Min Act: -0.0001

Data Index: 846719 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2348. Min Act: -0.0001

Data Index: 822710 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1038344 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2048. Min Act: -0.0001

Data Index: 219128 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2048. Min Act: -0.0001

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2091. Min Act: -0.0002

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1950. Min Act: -0.0001

Data Index: 60702 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2002. Min Act: -0.0001

Data Index: 171669 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1315335 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1786. Min Act: -0.0001

Data Index: 168871 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1944. Min Act: -0.0001

Data Index: 688884 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1729. Min Act: -0.0001

Data Index: 19802 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1849. Min Act: -0.0001

Data Index: 696036 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1309892 (C4 (Web Text))

Max Activating Token Index: 283