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

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

Neuron 517 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.6905. Min Act: -0.0000

Data Index: 660635 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.2611. Min Act: -0.0000

Data Index: 455793 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.3934. Min Act: -0.0000

Data Index: 999273 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.1917. Min Act: -0.0000

Data Index: 70222 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.2006. Min Act: -0.0000

Data Index: 395003 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.1889. Min Act: -0.0000

Data Index: 318613 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0948. Min Act: -0.0000

Data Index: 701872 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0913. Min Act: -0.0000

Data Index: 319037 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0938. Min Act: -0.0000

Data Index: 699119 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0482. Min Act: -0.0000

Data Index: 746147 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0554. Min Act: -0.0000

Data Index: 710536 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.1635. Min Act: -0.0000

Data Index: 476244 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1093460 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.1146. Min Act: -0.0000

Data Index: 379161 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.6905. Min Range: -1.6905

Max Act: 0.9906. Min Act: -0.0000

Data Index: 879206 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1059764 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0304. Min Act: -0.0000

Data Index: 461298 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.6905. Min Range: -1.6905

Max Act: 0.9810. Min Act: -0.0000

Data Index: 320166 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0330. Min Act: -0.0000

Data Index: 687223 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.6905. Min Range: -1.6905

Max Act: 1.0261. Min Act: -0.0000

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 953