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

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

Neuron 2649 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.2197. Min Act: -0.0002

Data Index: 646351 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1900. Min Act: -0.0002

Data Index: 181799 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1876. Min Act: -0.0002

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1835. Min Act: -0.0002

Data Index: 233008 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1831. Min Act: -0.0002

Data Index: 1198608 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1770. Min Act: -0.0002

Data Index: 899706 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1785. Min Act: -0.0002

Data Index: 666729 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1730. Min Act: -0.0002

Data Index: 670010 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1767. Min Act: -0.0002

Data Index: 803076 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1797. Min Act: -0.0002

Data Index: 717216 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1788. Min Act: -0.0002

Data Index: 671828 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1753. Min Act: -0.0002

Data Index: 587190 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1748. Min Act: -0.0002

Data Index: 1243906 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1792. Min Act: -0.0002

Data Index: 683781 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1733. Min Act: -0.0002

Data Index: 435201 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1703. Min Act: -0.0002

Data Index: 1108116 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1715. Min Act: -0.0002

Data Index: 259902 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1705. Min Act: -0.0002

Data Index: 280178 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1695. Min Act: -0.0002

Data Index: 526590 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1710. Min Act: -0.0002

Data Index: 1180830 (C4 (Web Text))

Max Activating Token Index: 244