Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0002

Data Index: 23524 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0892. Min Act: -0.0002

Data Index: 252693 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0883. Min Act: -0.0002

Data Index: 600568 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0887. Min Act: -0.0002

Data Index: 977217 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0857. Min Act: -0.0002

Data Index: 208045 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1101084 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0819. Min Act: -0.0002

Data Index: 273430 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1050449 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0799. Min Act: -0.0002

Data Index: 4244 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0774. Min Act: -0.0002

Data Index: 83295 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0768. Min Act: -0.0002

Data Index: 222656 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1018417 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0766. Min Act: -0.0002

Data Index: 727156 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0750. Min Act: -0.0002

Data Index: 368206 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0751. Min Act: -0.0002

Data Index: 302898 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1289045 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0742. Min Act: -0.0002

Data Index: 135021 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0747. Min Act: -0.0002

Data Index: 975915 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0723. Min Act: -0.0002

Data Index: 264370 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0714. Min Act: -0.0002

Data Index: 893028 (C4 (Web Text))

Max Activating Token Index: 770