Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0003

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0873. Min Act: -0.0003

Data Index: 23371 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0876. Min Act: -0.0004

Data Index: 231306 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0874. Min Act: -0.0003

Data Index: 530338 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0866. Min Act: -0.0003

Data Index: 384347 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0838. Min Act: -0.0003

Data Index: 607383 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0802. Min Act: -0.0003

Data Index: 663200 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0797. Min Act: -0.0003

Data Index: 166450 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0809. Min Act: -0.0003

Data Index: 955253 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0802. Min Act: -0.0003

Data Index: 248330 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0768. Min Act: -0.0003

Data Index: 761867 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0790. Min Act: -0.0003

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0780. Min Act: -0.0003

Data Index: 1160503 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0740. Min Act: -0.0003

Data Index: 866321 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0739. Min Act: -0.0003

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1272023 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0704. Min Act: -0.0003

Data Index: 556081 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1035402 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0742. Min Act: -0.0003

Data Index: 1233391 (C4 (Web Text))

Max Activating Token Index: 757