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

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

Neuron 3728 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2330. Min Act: -0.0000

Data Index: 606297 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2094. Min Act: -0.0000

Data Index: 92173 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2242. Min Act: -0.0000

Data Index: 516007 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2169. Min Act: -0.0000

Data Index: 280964 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2152. Min Act: -0.0000

Data Index: 273445 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1328919 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1974. Min Act: -0.0000

Data Index: 271850 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1071287 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1792. Min Act: -0.0000

Data Index: 556674 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1822. Min Act: -0.0000

Data Index: 982713 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1829. Min Act: -0.0000

Data Index: 318241 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1733. Min Act: -0.0000

Data Index: 596253 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1786. Min Act: -0.0000

Data Index: 172761 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1781. Min Act: -0.0000

Data Index: 375893 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1732. Min Act: -0.0000

Data Index: 883405 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1838. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1280920 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1797. Min Act: -0.0000

Data Index: 461088 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1741. Min Act: -0.0000

Data Index: 555039 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.2330. Min Range: -0.2330

Max Act: 0.1730. Min Act: 0.0000

Data Index: 342029 (C4 (Web Text))

Max Activating Token Index: 500