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

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

Neuron 3730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.7025. Min Act: -0.0000

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.4750. Min Act: -0.0000

Data Index: 711275 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.2713. Min Act: -0.0000

Data Index: 955741 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1217954 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1946. Min Act: -0.0000

Data Index: 359660 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.2975. Min Act: -0.0000

Data Index: 626888 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1139247 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1497. Min Act: -0.0000

Data Index: 372121 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1054. Min Act: -0.0000

Data Index: 517951 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1335. Min Act: -0.0000

Data Index: 961430 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1224855 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0725. Min Act: -0.0000

Data Index: 653318 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1085636 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1255057 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0426. Min Act: -0.0000

Data Index: 106544 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1254194 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0610. Min Act: -0.0000

Data Index: 820498 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1293452 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.1541. Min Act: -0.0000

Data Index: 605308 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.7025. Min Range: -1.7025

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1110286 (C4 (Web Text))

Max Activating Token Index: 231