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

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

Neuron 5344 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: 2.8713. Min Range: -2.8713

Max Act: 2.8713. Min Act: -0.0000

Data Index: 1210454 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.7300. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.5781. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.4901. Min Act: -0.0000

Data Index: 241901 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.0922. Min Act: -0.0000

Data Index: 555605 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.1537. Min Act: -0.0000

Data Index: 60036 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.1188. Min Act: -0.0000

Data Index: 483174 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.0355. Min Act: -0.0000

Data Index: 907884 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.0690. Min Act: -0.0000

Data Index: 1143851 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1061383 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 2.8713. Min Range: -2.8713

Max Act: 2.0558. Min Act: -0.0000

Data Index: 1184264 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.9363. Min Act: -0.0000

Data Index: 753164 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.9374. Min Act: -0.0000

Data Index: 1327670 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.8192. Min Act: -0.0000

Data Index: 220813 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1045695 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.9898. Min Act: -0.0000

Data Index: 327220 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.9382. Min Act: -0.0000

Data Index: 927638 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.8248. Min Act: -0.0000

Data Index: 710681 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 2.8713. Min Range: -2.8713

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1029015 (C4 (Web Text))

Max Activating Token Index: 700