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

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

Neuron 1902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1668. Min Act: -0.0001

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1268882 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1523. Min Act: -0.0001

Data Index: 746980 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1588. Min Act: -0.0001

Data Index: 532218 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1464. Min Act: -0.0001

Data Index: 8752 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1314. Min Act: -0.0001

Data Index: 475029 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1187. Min Act: -0.0001

Data Index: 908530 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1309. Min Act: -0.0001

Data Index: 986793 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1352228 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1195. Min Act: -0.0001

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1210. Min Act: -0.0001

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1219. Min Act: -0.0001

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1195. Min Act: -0.0001

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1107. Min Act: -0.0001

Data Index: 84914 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1091. Min Act: -0.0001

Data Index: 651890 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1004284 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1030. Min Act: -0.0001

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1035. Min Act: -0.0001

Data Index: 61075 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1050. Min Act: -0.0001

Data Index: 618157 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1255024 (C4 (Web Text))

Max Activating Token Index: 462