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

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

Neuron 1688 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: 0.1307. Min Range: -0.1307

Max Act: 0.1182. Min Act: -0.0002

Data Index: 858611 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1196549 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1035727 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1275. Min Act: -0.0002

Data Index: 177230 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1131. Min Act: -0.0002

Data Index: 648204 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1121. Min Act: -0.0002

Data Index: 71909 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1168. Min Act: -0.0002

Data Index: 260835 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1121512 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0959. Min Act: -0.0002

Data Index: 220268 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0988. Min Act: -0.0002

Data Index: 364042 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1146. Min Act: -0.0002

Data Index: 289961 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1307. Min Act: -0.0002

Data Index: 638368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1016. Min Act: -0.0002

Data Index: 6975 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1008. Min Act: -0.0002

Data Index: 562775 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1077. Min Act: -0.0002

Data Index: 819393 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1034520 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0961. Min Act: -0.0002

Data Index: 796865 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0869. Min Act: -0.0002

Data Index: 763145 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1212923 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1307. Min Range: -0.1307

Max Act: 0.0988. Min Act: -0.0002

Data Index: 877302 (C4 (Web Text))

Max Activating Token Index: 47