Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.8420. Min Act: -0.0001

Data Index: 59404 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.6582. Min Act: -0.0001

Data Index: 975597 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.6860. Min Act: -0.0001

Data Index: 9696 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.7231. Min Act: -0.0001

Data Index: 1134300 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.5935. Min Act: -0.0001

Data Index: 1249034 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.5215. Min Act: -0.0001

Data Index: 971453 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.5183. Min Act: -0.0001

Data Index: 946741 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.4521. Min Act: -0.0001

Data Index: 918376 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.3692. Min Act: -0.0001

Data Index: 1061387 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.4497. Min Act: -0.0001

Data Index: 925125 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.3027. Min Act: -0.0001

Data Index: 643910 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2988. Min Act: -0.0001

Data Index: 638495 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.3347. Min Act: -0.0001

Data Index: 1076664 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.3367. Min Act: -0.0001

Data Index: 562972 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2972. Min Act: -0.0001

Data Index: 354060 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1000032 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2478. Min Act: -0.0001

Data Index: 709659 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2156. Min Act: -0.0001

Data Index: 699136 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2004. Min Act: -0.0001

Data Index: 671801 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.8420. Min Range: -1.8420

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1169480 (C4 (Web Text))

Max Activating Token Index: 86