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

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

Neuron 4445 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.4836. Min Act: -0.0000

Data Index: 137113 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.1199. Min Act: -0.0000

Data Index: 513535 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.1299. Min Act: -0.0000

Data Index: 394423 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.1003. Min Act: -0.0000

Data Index: 362834 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.0338. Min Act: -0.0000

Data Index: 265666 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.0427. Min Act: -0.0000

Data Index: 29052 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 2.4836. Min Range: -2.4836

Max Act: 2.0064. Min Act: -0.0000

Data Index: 352650 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1094566 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7879. Min Act: -0.0000

Data Index: 1142449 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7451. Min Act: -0.0000

Data Index: 318805 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7335. Min Act: -0.0000

Data Index: 975112 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7040. Min Act: -0.0000

Data Index: 1130021 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7201. Min Act: -0.0000

Data Index: 623705 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7258. Min Act: -0.0000

Data Index: 795109 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.6936. Min Act: -0.0000

Data Index: 1189649 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1190311 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.6508. Min Act: -0.0000

Data Index: 83600 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1016499 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.7155. Min Act: -0.0000

Data Index: 1297974 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 2.4836. Min Range: -2.4836

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1129929 (C4 (Web Text))

Max Activating Token Index: 116