Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4282 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5307. Min Act: -0.0001

Data Index: 831727 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1356873 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1236738 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5607. Min Act: -0.0001

Data Index: 313332 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4762. Min Act: -0.0001

Data Index: 25314 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5049. Min Act: -0.0001

Data Index: 250275 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5195. Min Act: -0.0001

Data Index: 364035 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5287. Min Act: -0.0001

Data Index: 954962 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5213. Min Act: -0.0001

Data Index: 716901 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1313375 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5031. Min Act: -0.0001

Data Index: 1252739 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4939. Min Act: -0.0001

Data Index: 96296 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1144287 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5264. Min Act: -0.0001

Data Index: 325701 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5479. Min Act: -0.0001

Data Index: 943567 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5226. Min Act: -0.0001

Data Index: 465745 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5068. Min Act: -0.0001

Data Index: 775305 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4849. Min Act: -0.0001

Data Index: 626284 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1114500 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4838. Min Act: -0.0001

Data Index: 252687 (C4 (Web Text))

Max Activating Token Index: 539