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

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

Neuron 1592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8353. Min Range: -5.8353

Max Act: 5.7971. Min Act: -0.0000

Data Index: 688689 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 5.8353. Min Range: -5.8353

Max Act: 5.8353. Min Act: -0.0000

Data Index: 1271507 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 5.8353. Min Range: -5.8353

Max Act: 5.5681. Min Act: -0.0000

Data Index: 65050 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 5.8353. Min Range: -5.8353

Max Act: 5.2264. Min Act: -0.0000

Data Index: 655048 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.5869. Min Act: -0.0000

Data Index: 1307999 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.9954. Min Act: -0.0000

Data Index: 1239860 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.6285. Min Act: -0.0000

Data Index: 1012667 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.7281. Min Act: -0.0000

Data Index: 210734 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2672. Min Act: -0.0000

Data Index: 50531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.5982. Min Act: -0.0000

Data Index: 938063 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2276. Min Act: -0.0000

Data Index: 1139266 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.3853. Min Act: -0.0000

Data Index: 273230 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2880. Min Act: -0.0000

Data Index: 181547 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2731. Min Act: -0.0000

Data Index: 672099 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2792. Min Act: -0.0000

Data Index: 647794 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.0646. Min Act: -0.0000

Data Index: 434535 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.3944. Min Act: -0.0000

Data Index: 225961 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2207. Min Act: -0.0000

Data Index: 1264824 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2378. Min Act: -0.0000

Data Index: 1080041 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 5.8353. Min Range: -5.8353

Max Act: 4.2021. Min Act: -0.0000

Data Index: 827771 (C4 (Web Text))

Max Activating Token Index: 359