Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1614. Min Act: -0.0003

Data Index: 593625 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1358. Min Act: -0.0003

Data Index: 1178140 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1254. Min Act: -0.0003

Data Index: 1274949 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1200. Min Act: -0.0003

Data Index: 675348 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1172. Min Act: -0.0003

Data Index: 60011 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1073. Min Act: -0.0003

Data Index: 49587 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1106. Min Act: -0.0003

Data Index: 1150890 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1144. Min Act: -0.0003

Data Index: 205960 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1131. Min Act: -0.0003

Data Index: 480220 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1153. Min Act: -0.0003

Data Index: 817635 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1071275 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1294245 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1099. Min Act: -0.0003

Data Index: 195595 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1086. Min Act: -0.0003

Data Index: 880274 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.0961. Min Act: -0.0003

Data Index: 602319 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1001. Min Act: -0.0003

Data Index: 652715 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1038. Min Act: -0.0003

Data Index: 462710 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1031. Min Act: -0.0003

Data Index: 1167522 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1066. Min Act: -0.0003

Data Index: 761785 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.1614. Min Range: -0.1614

Max Act: 0.1026. Min Act: -0.0003

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 537