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

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

Neuron 553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1115841 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1004903 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.7357. Min Act: -0.0000

Data Index: 876159 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.7320. Min Act: -0.0000

Data Index: 564659 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6716. Min Act: -0.0000

Data Index: 987641 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6007. Min Act: -0.0000

Data Index: 95185 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1062295 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6295. Min Act: -0.0000

Data Index: 774555 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6498. Min Act: -0.0000

Data Index: 474339 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6253. Min Act: -0.0000

Data Index: 130523 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6295. Min Act: -0.0000

Data Index: 208937 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6299. Min Act: -0.0000

Data Index: 759908 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6178. Min Act: -0.0000

Data Index: 522914 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.5711. Min Act: -0.0000

Data Index: 872299 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.5764. Min Act: -0.0000

Data Index: 461470 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6244. Min Act: -0.0000

Data Index: 838116 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1492487 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.5783. Min Act: -0.0000

Data Index: 423734 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.5979. Min Act: -0.0000

Data Index: 735683 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.8832. Min Range: -0.8832

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1302506 (C4 (Web Text))

Max Activating Token Index: 698