Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1486 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1068498 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2068. Min Act: -0.0002

Data Index: 231375 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2065. Min Act: -0.0002

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2099. Min Act: -0.0002

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2009. Min Act: -0.0002

Data Index: 55467 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1973. Min Act: -0.0002

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1912. Min Act: -0.0001

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1865. Min Act: -0.0002

Data Index: 431245 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2030. Min Act: -0.0002

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1766. Min Act: -0.0002

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1749. Min Act: -0.0002

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1817. Min Act: -0.0002

Data Index: 1259099 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1641. Min Act: -0.0002

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1821. Min Act: -0.0001

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1880. Min Act: -0.0002

Data Index: 1097706 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1805. Min Act: -0.0002

Data Index: 1289685 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1799. Min Act: -0.0001

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1856. Min Act: -0.0002

Data Index: 370439 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1179522 (C4 (Web Text))

Max Activating Token Index: 175