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

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

Neuron 4712 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.6587. Min Act: -0.0000

Data Index: 1264322 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.1285. Min Act: -0.0000

Data Index: 901274 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.1599. Min Act: -0.0000

Data Index: 895695 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.1344. Min Act: -0.0000

Data Index: 998318 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.0022. Min Act: -0.0000

Data Index: 816197 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.6587. Min Range: -1.6587

Max Act: 1.0008. Min Act: -0.0000

Data Index: 850406 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.9685. Min Act: -0.0000

Data Index: 799558 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.9255. Min Act: -0.0000

Data Index: 389693 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.8187. Min Act: -0.0000

Data Index: 141529 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.8065. Min Act: -0.0000

Data Index: 940170 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.8097. Min Act: -0.0000

Data Index: 803251 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.8003. Min Act: -0.0000

Data Index: 568722 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.8183. Min Act: -0.0000

Data Index: 974165 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7704. Min Act: -0.0000

Data Index: 321910 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7544. Min Act: -0.0000

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7657. Min Act: -0.0000

Data Index: 41749 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7426. Min Act: -0.0000

Data Index: 195200 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7955. Min Act: -0.0000

Data Index: 405291 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.7013. Min Act: -0.0000

Data Index: 439313 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.6587. Min Range: -1.6587

Max Act: 0.6754. Min Act: -0.0000

Data Index: 971247 (C4 (Web Text))

Max Activating Token Index: 339