Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 899 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0003

Data Index: 1508160 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1112. Min Act: -0.0003

Data Index: 1631393 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1119. Min Act: -0.0003

Data Index: 1576579 (Python Code)

Max Activating Token Index: 743

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1510235 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1041. Min Act: -0.0003

Data Index: 1456696 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1074. Min Act: -0.0003

Data Index: 1515898 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1153. Min Act: -0.0003

Data Index: 1364044 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1045. Min Act: -0.0003

Data Index: 1370686 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1441394 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1065. Min Act: -0.0003

Data Index: 1645079 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1426225 (Python Code)

Max Activating Token Index: 352

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1558853 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1009. Min Act: -0.0003

Data Index: 1506673 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1545584 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1017. Min Act: -0.0003

Data Index: 1522383 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1397331 (Python Code)

Max Activating Token Index: 947

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1632659 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1587992 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1462496 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0988. Min Act: -0.0003

Data Index: 1459608 (Python Code)

Max Activating Token Index: 438