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

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

Neuron 118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1264313 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1270679 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1863. Min Act: -0.0002

Data Index: 516706 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1856. Min Act: -0.0002

Data Index: 694964 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1843. Min Act: -0.0002

Data Index: 424980 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1760. Min Act: -0.0002

Data Index: 746451 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1737. Min Act: -0.0002

Data Index: 754993 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1800. Min Act: -0.0002

Data Index: 247476 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1797. Min Act: -0.0002

Data Index: 27895 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1787. Min Act: -0.0002

Data Index: 1025927 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1779. Min Act: -0.0002

Data Index: 90741 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1668. Min Act: -0.0002

Data Index: 742208 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1765. Min Act: -0.0002

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1747. Min Act: -0.0002

Data Index: 384397 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1809. Min Act: -0.0002

Data Index: 546390 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1722. Min Act: -0.0002

Data Index: 1093844 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1721. Min Act: -0.0002

Data Index: 650741 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1646. Min Act: -0.0002

Data Index: 973947 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1762. Min Act: -0.0002

Data Index: 918370 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1757. Min Act: -0.0002

Data Index: 794910 (C4 (Web Text))

Max Activating Token Index: 569