Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 238 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1597499 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1505421 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1720. Min Act: -0.0001

Data Index: 1636500 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1530. Min Act: -0.0001

Data Index: 1628631 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1534619 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1455. Min Act: -0.0001

Data Index: 68844 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1582517 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1353. Min Act: -0.0001

Data Index: 1619134 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1090610 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1987. Min Act: -0.0000

Data Index: 1409363 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1264. Min Act: -0.0001

Data Index: 1378370 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1432835 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1171. Min Act: -0.0000

Data Index: 708301 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1053. Min Act: -0.0001

Data Index: 1371840 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0914. Min Act: -0.0001

Data Index: 1636313 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1439169 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1146. Min Act: -0.0001

Data Index: 1421320 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0178. Min Act: -0.0001

Data Index: 1507968 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1503266 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1134. Min Act: -0.0001

Data Index: 1507897 (Python Code)

Max Activating Token Index: 424