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

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

Neuron 2426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1317. Min Range: -7.1317

Max Act: 7.1317. Min Act: -0.0000

Data Index: 649611 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.9617. Min Act: -0.0000

Data Index: 1222175 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.5014. Min Act: -0.0000

Data Index: 629171 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.6563. Min Act: -0.0000

Data Index: 1128077 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.4365. Min Act: -0.0000

Data Index: 369434 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.2709. Min Act: -0.0000

Data Index: 882458 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.4396. Min Act: -0.0000

Data Index: 1207924 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.2581. Min Act: -0.0000

Data Index: 462921 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.4366. Min Act: -0.0000

Data Index: 1023108 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.2458. Min Act: -0.0000

Data Index: 186158 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.7107. Min Act: -0.0000

Data Index: 766481 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.2468. Min Act: -0.0000

Data Index: 494891 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.6144. Min Act: -0.0000

Data Index: 129022 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.8971. Min Act: -0.0000

Data Index: 1129739 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.7067. Min Act: -0.0000

Data Index: 926404 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.6968. Min Act: -0.0000

Data Index: 381285 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 7.1317. Min Range: -7.1317

Max Act: 6.1250. Min Act: -0.0000

Data Index: 748302 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.7714. Min Act: -0.0000

Data Index: 1302931 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.4479. Min Act: -0.0000

Data Index: 1318186 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 7.1317. Min Range: -7.1317

Max Act: 5.5343. Min Act: -0.0000

Data Index: 189824 (C4 (Web Text))

Max Activating Token Index: 748