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

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

Neuron 640 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2282. Min Act: -0.0000

Data Index: 491589 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1225084 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2068. Min Act: -0.0000

Data Index: 929820 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1043749 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1338633 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2017. Min Act: -0.0000

Data Index: 540711 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.2054. Min Act: -0.0000

Data Index: 818723 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1886. Min Act: -0.0000

Data Index: 696195 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1254709 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1921. Min Act: -0.0000

Data Index: 123416 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1777. Min Act: -0.0000

Data Index: 733976 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1241552 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1820. Min Act: -0.0000

Data Index: 926421 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1782. Min Act: -0.0000

Data Index: 126928 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1678. Min Act: -0.0000

Data Index: 248507 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1449. Min Act: -0.0000

Data Index: 637292 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1678. Min Act: -0.0000

Data Index: 808148 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1746. Min Act: 0.0000

Data Index: 795623 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1162539 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.2282. Min Range: -0.2282

Max Act: 0.1668. Min Act: -0.0000

Data Index: 875501 (C4 (Web Text))

Max Activating Token Index: 25