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

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

Neuron 1210 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4623. Min Range: -4.4623

Max Act: 4.4623. Min Act: -0.0000

Data Index: 1322962 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 4.4623. Min Range: -4.4623

Max Act: 2.3506. Min Act: -0.0000

Data Index: 756973 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 4.4623. Min Range: -4.4623

Max Act: 2.4038. Min Act: -0.0000

Data Index: 198106 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 4.4623. Min Range: -4.4623

Max Act: 2.2134. Min Act: -0.0000

Data Index: 270563 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 4.4623. Min Range: -4.4623

Max Act: 2.1306. Min Act: -0.0000

Data Index: 388181 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.9649. Min Act: -0.0000

Data Index: 552944 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.8274. Min Act: -0.0000

Data Index: 345981 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.8170. Min Act: -0.0000

Data Index: 597522 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.6969. Min Act: -0.0000

Data Index: 222663 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.6540. Min Act: -0.0000

Data Index: 987348 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.6262. Min Act: -0.0000

Data Index: 449825 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.5133. Min Act: -0.0000

Data Index: 551236 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.5734. Min Act: -0.0000

Data Index: 73771 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.5536. Min Act: -0.0000

Data Index: 246288 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.5308. Min Act: -0.0000

Data Index: 370940 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.4235. Min Act: -0.0000

Data Index: 146422 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.5232. Min Act: -0.0000

Data Index: 1336413 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.4051. Min Act: -0.0000

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.3497. Min Act: -0.0000

Data Index: 508203 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 4.4623. Min Range: -4.4623

Max Act: 1.2887. Min Act: -0.0000

Data Index: 143752 (C4 (Web Text))

Max Activating Token Index: 240