Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2389. Min Act: -0.0003

Data Index: 861238 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2121. Min Act: -0.0003

Data Index: 582138 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2086. Min Act: -0.0003

Data Index: 721757 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1897. Min Act: -0.0003

Data Index: 99932 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2032. Min Act: -0.0003

Data Index: 943573 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1855. Min Act: -0.0003

Data Index: 250867 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2064. Min Act: -0.0003

Data Index: 1081482 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2027. Min Act: -0.0003

Data Index: 1112190 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1704. Min Act: -0.0003

Data Index: 688546 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1874. Min Act: -0.0003

Data Index: 467331 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1844. Min Act: -0.0003

Data Index: 1315302 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1929. Min Act: -0.0003

Data Index: 165373 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1750. Min Act: -0.0003

Data Index: 85207 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1751. Min Act: -0.0003

Data Index: 152800 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.2022. Min Act: -0.0003

Data Index: 1011340 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1815. Min Act: -0.0003

Data Index: 1115637 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1870. Min Act: -0.0003

Data Index: 418742 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1888. Min Act: -0.0003

Data Index: 1273383 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1672. Min Act: -0.0003

Data Index: 881071 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.2389. Min Range: -0.2389

Max Act: 0.1743. Min Act: -0.0003

Data Index: 674375 (C4 (Web Text))

Max Activating Token Index: 697