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

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

Neuron 4924 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: 0.1832. Min Range: -0.1832

Max Act: 0.1832. Min Act: -0.0002

Data Index: 180523 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1157. Min Act: -0.0002

Data Index: 740994 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1204. Min Act: -0.0002

Data Index: 562574 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1194. Min Act: -0.0002

Data Index: 914428 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1134. Min Act: -0.0002

Data Index: 120531 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1009. Min Act: -0.0002

Data Index: 478626 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1023. Min Act: -0.0002

Data Index: 290591 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1094. Min Act: -0.0002

Data Index: 987206 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1004. Min Act: -0.0002

Data Index: 294906 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1001. Min Act: -0.0002

Data Index: 479405 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1034. Min Act: -0.0002

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1140. Min Act: -0.0002

Data Index: 257682 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1025. Min Act: -0.0002

Data Index: 873655 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1186210 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0981. Min Act: -0.0002

Data Index: 913076 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1041539 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1192559 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0915. Min Act: -0.0002

Data Index: 713565 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.1024. Min Act: -0.0002

Data Index: 603782 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.1832. Min Range: -0.1832

Max Act: 0.0976. Min Act: -0.0002

Data Index: 120833 (C4 (Web Text))

Max Activating Token Index: 674