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

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

Neuron 4847 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2649. Min Act: -0.0000

Data Index: 817632 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2513. Min Act: -0.0000

Data Index: 700379 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1306430 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2101. Min Act: -0.0000

Data Index: 574132 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2234. Min Act: -0.0000

Data Index: 75355 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2301. Min Act: -0.0000

Data Index: 670367 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1092470 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1961. Min Act: -0.0000

Data Index: 985590 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1038695 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1894. Min Act: -0.0000

Data Index: 946074 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1926. Min Act: -0.0000

Data Index: 844015 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1827. Min Act: -0.0000

Data Index: 408153 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1826. Min Act: -0.0000

Data Index: 86480 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1834. Min Act: -0.0000

Data Index: 24395 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1950. Min Act: -0.0000

Data Index: 416843 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1352878 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1965. Min Act: -0.0000

Data Index: 419494 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1880. Min Act: -0.0000

Data Index: 159718 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1303346 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1009609 (C4 (Web Text))

Max Activating Token Index: 984