Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3211 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.1836. Min Act: -0.0002

Data Index: 75567 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0925. Min Act: -0.0002

Data Index: 128837 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0000. Min Act: -0.0002

Data Index: 1083321 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0299. Min Act: -0.0002

Data Index: 1082270 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0487. Min Act: -0.0002

Data Index: 985954 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0776. Min Act: -0.0002

Data Index: 517798 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0685. Min Act: -0.0002

Data Index: 16355 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9930. Min Act: -0.0002

Data Index: 526249 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9293. Min Act: -0.0002

Data Index: 610294 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0234. Min Act: -0.0002

Data Index: 1278076 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0143. Min Act: -0.0002

Data Index: 1085297 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9857. Min Act: -0.0002

Data Index: 705893 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9851. Min Act: -0.0002

Data Index: 707320 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.1836. Min Range: -1.1836

Max Act: 1.0009. Min Act: -0.0002

Data Index: 1049142 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.8704. Min Act: -0.0002

Data Index: 216803 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9228. Min Act: -0.0002

Data Index: 408082 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.8848. Min Act: -0.0002

Data Index: 403200 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9367. Min Act: -0.0002

Data Index: 193653 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9080. Min Act: -0.0002

Data Index: 595204 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 1.1836. Min Range: -1.1836

Max Act: 0.9080. Min Act: -0.0002

Data Index: 835943 (C4 (Web Text))

Max Activating Token Index: 388