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

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

Neuron 1531 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1264215 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1052. Min Act: -0.0002

Data Index: 295700 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0900. Min Act: -0.0002

Data Index: 20080 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0998. Min Act: -0.0002

Data Index: 677748 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0919. Min Act: -0.0002

Data Index: 152162 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0936. Min Act: -0.0002

Data Index: 863915 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0918. Min Act: -0.0002

Data Index: 358946 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0926. Min Act: -0.0002

Data Index: 667355 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0894. Min Act: -0.0002

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1332535 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0865. Min Act: -0.0002

Data Index: 290388 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1034775 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0871. Min Act: -0.0002

Data Index: 541762 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0874. Min Act: -0.0002

Data Index: 352505 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0742. Min Act: -0.0002

Data Index: 404168 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0863. Min Act: -0.0002

Data Index: 423870 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0860. Min Act: -0.0002

Data Index: 32637 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0901. Min Act: -0.0002

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 275