Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4810 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1573146 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1939. Min Act: -0.0000

Data Index: 543890 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1348. Min Act: 0.0000

Data Index: 400009 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1558882 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1539441 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1302. Min Act: -0.0000

Data Index: 781723 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1514667 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1632554 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1224. Min Act: -0.0000

Data Index: 170762 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1636006 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1088745 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1636769 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1027835 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1548561 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1077972 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1014. Min Act: -0.0000

Data Index: 384586 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1393803 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1025. Min Act: -0.0000

Data Index: 360334 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1082959 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.2327. Min Range: -0.2327

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1558285 (Python Code)

Max Activating Token Index: 350