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

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

Neuron 2419 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1148696 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0779. Min Act: -0.0001

Data Index: 554882 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1324128 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0723. Min Act: -0.0001

Data Index: 369171 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0773. Min Act: -0.0001

Data Index: 69195 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0742. Min Act: -0.0001

Data Index: 14123 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0732. Min Act: -0.0001

Data Index: 966941 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0758. Min Act: -0.0001

Data Index: 220831 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0675. Min Act: -0.0001

Data Index: 257711 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0746. Min Act: -0.0001

Data Index: 649166 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0692. Min Act: -0.0001

Data Index: 672995 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0696. Min Act: -0.0001

Data Index: 956568 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1187518 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1141379 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0689. Min Act: -0.0001

Data Index: 743507 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1263256 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0680. Min Act: -0.0001

Data Index: 275954 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0700. Min Act: -0.0001

Data Index: 941038 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0704. Min Act: -0.0001

Data Index: 860278 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0661. Min Act: -0.0001

Data Index: 444828 (C4 (Web Text))

Max Activating Token Index: 887