Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1879 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 794891 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1102. Min Act: -0.0001

Data Index: 876583 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1148929 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0894. Min Act: -0.0001

Data Index: 958665 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1141292 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0848. Min Act: -0.0001

Data Index: 345188 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0849. Min Act: -0.0001

Data Index: 801399 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0856. Min Act: -0.0001

Data Index: 681727 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0796. Min Act: -0.0001

Data Index: 867360 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0789. Min Act: -0.0001

Data Index: 278173 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0739. Min Act: -0.0001

Data Index: 991355 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0766. Min Act: -0.0001

Data Index: 599014 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1274630 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0722. Min Act: -0.0001

Data Index: 403004 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0746. Min Act: -0.0001

Data Index: 274682 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0740. Min Act: -0.0001

Data Index: 70615 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0750. Min Act: -0.0001

Data Index: 100638 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0692. Min Act: -0.0001

Data Index: 60182 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0754. Min Act: -0.0001

Data Index: 762857 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0739. Min Act: -0.0001

Data Index: 557547 (C4 (Web Text))

Max Activating Token Index: 92