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

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

Neuron 2595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0004

Data Index: 1534849 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1185. Min Act: -0.0004

Data Index: 1415766 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1197. Min Act: -0.0004

Data Index: 1621876 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1095. Min Act: -0.0004

Data Index: 1504868 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1242. Min Act: -0.0004

Data Index: 1647400 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1101. Min Act: -0.0004

Data Index: 1435365 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1047. Min Act: -0.0004

Data Index: 1599200 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1171. Min Act: -0.0004

Data Index: 1650022 (Python Code)

Max Activating Token Index: 809

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1118. Min Act: -0.0004

Data Index: 1534456 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1217. Min Act: -0.0004

Data Index: 1564181 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1046. Min Act: -0.0004

Data Index: 1638763 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1027. Min Act: -0.0004

Data Index: 1464392 (Python Code)

Max Activating Token Index: 952

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1054. Min Act: -0.0004

Data Index: 1399904 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1053. Min Act: -0.0004

Data Index: 1522156 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1134. Min Act: -0.0004

Data Index: 1414105 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1004. Min Act: -0.0004

Data Index: 1615175 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1045. Min Act: -0.0004

Data Index: 1607211 (Python Code)

Max Activating Token Index: 776

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1050. Min Act: -0.0004

Data Index: 1437941 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0968. Min Act: -0.0004

Data Index: 1651790 (Python Code)

Max Activating Token Index: 181

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1041. Min Act: -0.0004

Data Index: 1646275 (Python Code)

Max Activating Token Index: 532