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

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

Neuron 4012 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1618. Min Act: -0.0002

Data Index: 252472 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1591. Min Act: -0.0002

Data Index: 796204 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.2250. Min Act: -0.0002

Data Index: 777256 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.2724. Min Act: -0.0002

Data Index: 1233154 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1247. Min Act: -0.0002

Data Index: 580299 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0772. Min Act: -0.0002

Data Index: 101395 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0703. Min Act: -0.0002

Data Index: 1039851 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1673. Min Act: -0.0002

Data Index: 1046341 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0686. Min Act: -0.0002

Data Index: 663151 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.1188. Min Act: -0.0002

Data Index: 938656 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0680. Min Act: -0.0002

Data Index: 208596 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0520. Min Act: -0.0002

Data Index: 547417 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0745. Min Act: -0.0002

Data Index: 916116 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0161. Min Act: -0.0002

Data Index: 428096 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9834. Min Act: -0.0002

Data Index: 1139047 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0907. Min Act: -0.0002

Data Index: 168793 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0773. Min Act: -0.0002

Data Index: 973331 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0557. Min Act: -0.0002

Data Index: 787779 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.2724. Min Range: -1.2724

Max Act: 1.0837. Min Act: -0.0002

Data Index: 698239 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.2724. Min Range: -1.2724

Max Act: 0.9563. Min Act: -0.0002

Data Index: 1019608 (C4 (Web Text))

Max Activating Token Index: 743