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

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

Neuron 113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3737. Min Range: -2.3737

Max Act: 2.3737. Min Act: -0.0000

Data Index: 765864 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1124797 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 2.3737. Min Range: -2.3737

Max Act: 2.1438. Min Act: -0.0000

Data Index: 359900 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.6841. Min Act: -0.0000

Data Index: 143746 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.4268. Min Act: -0.0000

Data Index: 462989 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1094536 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2370. Min Act: -0.0000

Data Index: 759078 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.3516. Min Act: -0.0000

Data Index: 751458 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1334522 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1237079 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.3733. Min Act: -0.0000

Data Index: 365473 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1255323 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.3444. Min Act: -0.0000

Data Index: 980560 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2438. Min Act: -0.0000

Data Index: 583925 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2106. Min Act: -0.0000

Data Index: 957653 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.2331. Min Act: -0.0000

Data Index: 400338 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.3825. Min Act: -0.0000

Data Index: 929734 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.1969. Min Act: -0.0000

Data Index: 770623 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1035032 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.3737. Min Range: -2.3737

Max Act: 1.1121. Min Act: -0.0000

Data Index: 50224 (C4 (Web Text))

Max Activating Token Index: 740