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

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

Neuron 109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.8258. Min Act: -0.0001

Data Index: 702982 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1188203 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7995. Min Act: -0.0001

Data Index: 882740 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6982. Min Act: -0.0001

Data Index: 426475 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7993. Min Act: -0.0001

Data Index: 888654 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1193453 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7361. Min Act: -0.0001

Data Index: 851037 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6864. Min Act: -0.0001

Data Index: 979528 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7589. Min Act: -0.0001

Data Index: 602040 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.8228. Min Act: -0.0001

Data Index: 1256331 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.8004. Min Act: -0.0001

Data Index: 98669 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7127. Min Act: -0.0001

Data Index: 530890 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6764. Min Act: -0.0001

Data Index: 156468 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1315790 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7076. Min Act: -0.0001

Data Index: 1215120 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7575. Min Act: -0.0001

Data Index: 28579 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6837. Min Act: -0.0001

Data Index: 778246 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.6814. Min Act: -0.0001

Data Index: 348573 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7999. Min Act: -0.0001

Data Index: 517582 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.8573. Min Range: -0.8573

Max Act: 0.7128. Min Act: -0.0001

Data Index: 514157 (C4 (Web Text))

Max Activating Token Index: 460