Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2153 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1690. Min Act: -0.0001

Data Index: 775256 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1369. Min Act: -0.0001

Data Index: 260260 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1323. Min Act: -0.0001

Data Index: 956276 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1127. Min Act: -0.0001

Data Index: 634970 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1087. Min Act: -0.0001

Data Index: 914109 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1064. Min Act: -0.0001

Data Index: 814626 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1308088 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1075. Min Act: -0.0001

Data Index: 150232 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1354559 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1347447 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1301611 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1019. Min Act: -0.0000

Data Index: 262711 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1020. Min Act: -0.0001

Data Index: 17553 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.0945. Min Act: -0.0001

Data Index: 799209 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1038. Min Act: -0.0001

Data Index: 284507 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1003. Min Act: -0.0000

Data Index: 723778 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.0995. Min Act: -0.0001

Data Index: 732869 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1001. Min Act: -0.0001

Data Index: 501371 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1080318 (C4 (Web Text))

Max Activating Token Index: 601