Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0005

Data Index: 1124347 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1115. Min Act: -0.0005

Data Index: 901462 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1079. Min Act: -0.0005

Data Index: 301891 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1031. Min Act: -0.0005

Data Index: 1185946 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0975. Min Act: -0.0005

Data Index: 790221 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0958. Min Act: -0.0005

Data Index: 725335 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0943. Min Act: -0.0005

Data Index: 1311505 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0910. Min Act: -0.0005

Data Index: 853924 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0901. Min Act: -0.0005

Data Index: 1085617 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0845. Min Act: -0.0005

Data Index: 681972 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0894. Min Act: -0.0005

Data Index: 995424 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0857. Min Act: -0.0005

Data Index: 1043475 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0813. Min Act: -0.0005

Data Index: 231755 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0827. Min Act: -0.0005

Data Index: 30478 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0865. Min Act: -0.0005

Data Index: 418787 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0806. Min Act: -0.0005

Data Index: 647552 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0799. Min Act: -0.0005

Data Index: 914274 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0756. Min Act: -0.0005

Data Index: 1146069 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0748. Min Act: -0.0005

Data Index: 188278 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0790. Min Act: -0.0005

Data Index: 1207406 (C4 (Web Text))

Max Activating Token Index: 287