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

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

Neuron 5846 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.1435. Min Act: -0.0000

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1307399 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1022054 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1001877 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.0103. Min Act: -0.0000

Data Index: 455621 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.0204. Min Act: -0.0000

Data Index: 761683 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.2018. Min Range: -1.2018

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1118492 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1568068 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9270. Min Act: -0.0000

Data Index: 390962 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.9194. Min Act: -0.0000

Data Index: 121913 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8657. Min Act: -0.0000

Data Index: 819342 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8652. Min Act: -0.0000

Data Index: 287910 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8880. Min Act: -0.0000

Data Index: 747326 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1582853 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8421. Min Act: -0.0000

Data Index: 171319 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.8212. Min Act: -0.0000

Data Index: 900195 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7737. Min Act: -0.0000

Data Index: 550943 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1377957 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7263. Min Act: -0.0000

Data Index: 192973 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.2018. Min Range: -1.2018

Max Act: 0.7683. Min Act: -0.0000

Data Index: 185311 (C4 (Web Text))

Max Activating Token Index: 964