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

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

Neuron 1903 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: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0003

Data Index: 848542 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1189. Min Act: -0.0003

Data Index: 152114 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1404. Min Act: -0.0003

Data Index: 429272 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1258. Min Act: -0.0003

Data Index: 1136461 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1343. Min Act: -0.0003

Data Index: 242816 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1254. Min Act: -0.0003

Data Index: 1098622 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1252. Min Act: -0.0003

Data Index: 198472 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1404. Min Act: -0.0003

Data Index: 1037604 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1226157 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1234. Min Act: -0.0003

Data Index: 960207 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1226. Min Act: -0.0003

Data Index: 112744 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1103. Min Act: -0.0003

Data Index: 831982 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1125. Min Act: -0.0003

Data Index: 333070 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1073. Min Act: -0.0003

Data Index: 582973 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1157953 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.0973. Min Act: -0.0003

Data Index: 445008 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1406. Min Act: -0.0003

Data Index: 755032 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1144. Min Act: -0.0003

Data Index: 320085 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1175. Min Act: -0.0003

Data Index: 1165712 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1181. Min Act: -0.0003

Data Index: 1260313 (C4 (Web Text))

Max Activating Token Index: 506