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

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

Neuron 2032 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1133751 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.1014. Min Act: -0.0000

Data Index: 14595 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.0107. Min Act: -0.0000

Data Index: 364119 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.0393. Min Act: -0.0000

Data Index: 705408 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.0003. Min Act: -0.0000

Data Index: 376219 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.9372. Min Act: -0.0000

Data Index: 650544 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.1014. Min Range: -1.1014

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1095389 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.9468. Min Act: -0.0000

Data Index: 66411 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.9598. Min Act: -0.0000

Data Index: 316038 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8901. Min Act: -0.0000

Data Index: 19782 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8857. Min Act: -0.0000

Data Index: 293655 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8801. Min Act: -0.0000

Data Index: 917144 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8891. Min Act: 0.0000

Data Index: 164426 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8788. Min Act: -0.0000

Data Index: 621152 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8768. Min Act: -0.0000

Data Index: 435907 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1068308 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8690. Min Act: -0.0000

Data Index: 874407 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1234607 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8517. Min Act: -0.0000

Data Index: 500768 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1014. Min Range: -1.1014

Max Act: 0.8525. Min Act: -0.0000

Data Index: 515203 (C4 (Web Text))

Max Activating Token Index: 157