Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.9977. Min Act: -0.0000

Data Index: 198722 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.8731. Min Act: 0.0003

Data Index: 309124 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.8196. Min Act: -0.0000

Data Index: 46102 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7766. Min Act: -0.0001

Data Index: 491912 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7937. Min Act: -0.0000

Data Index: 868655 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1317328 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7122. Min Act: -0.0000

Data Index: 477118 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7550. Min Act: -0.0000

Data Index: 985939 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7478. Min Act: 0.0000

Data Index: 1024913 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7486. Min Act: -0.0000

Data Index: 640289 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6903. Min Act: -0.0001

Data Index: 1238321 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6889. Min Act: -0.0000

Data Index: 558986 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7242. Min Act: -0.0000

Data Index: 136406 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1119267 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.7024. Min Act: -0.0000

Data Index: 97698 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6578. Min Act: -0.0000

Data Index: 115064 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1175031 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6850. Min Act: -0.0000

Data Index: 492497 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1217258 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.9977. Min Range: -0.9977

Max Act: 0.6516. Min Act: -0.0000

Data Index: 645621 (C4 (Web Text))

Max Activating Token Index: 161