Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1876 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2374. Min Act: -0.0003

Data Index: 745691 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2430. Min Act: -0.0003

Data Index: 912485 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2192. Min Act: -0.0003

Data Index: 301214 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2210. Min Act: -0.0003

Data Index: 54662 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2141. Min Act: -0.0003

Data Index: 1258813 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2100. Min Act: -0.0003

Data Index: 333888 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2041. Min Act: -0.0003

Data Index: 855544 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1992. Min Act: -0.0003

Data Index: 1091708 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1887. Min Act: -0.0003

Data Index: 488234 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1958. Min Act: -0.0003

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2060. Min Act: -0.0003

Data Index: 345224 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1850. Min Act: -0.0003

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1810. Min Act: -0.0003

Data Index: 830462 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1281148 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1866. Min Act: -0.0003

Data Index: 682167 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1721. Min Act: -0.0003

Data Index: 328309 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1785. Min Act: -0.0002

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1864. Min Act: -0.0004

Data Index: 801853 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1906. Min Act: -0.0002

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1851. Min Act: -0.0003

Data Index: 941050 (C4 (Web Text))

Max Activating Token Index: 752