Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 196 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0796. Min Act: -0.0000

Data Index: 107876 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1143601 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0924. Min Act: -0.0000

Data Index: 985430 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9734. Min Act: -0.0000

Data Index: 610696 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 1.0924. Min Range: -1.0924

Max Act: 1.0253. Min Act: -0.0000

Data Index: 686060 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9642. Min Act: -0.0001

Data Index: 25445 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.9572. Min Act: -0.0001

Data Index: 122203 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8996. Min Act: -0.0000

Data Index: 608903 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8949. Min Act: -0.0000

Data Index: 920550 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8688. Min Act: -0.0000

Data Index: 428400 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1082684 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8827. Min Act: -0.0000

Data Index: 162268 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8277. Min Act: -0.0001

Data Index: 817588 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8753. Min Act: -0.0001

Data Index: 559576 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1288785 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1346577 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8888. Min Act: -0.0001

Data Index: 37405 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8702. Min Act: -0.0001

Data Index: 667970 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.8597. Min Act: -0.0001

Data Index: 266649 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.0924. Min Range: -1.0924

Max Act: 0.7994. Min Act: -0.0000

Data Index: 577032 (C4 (Web Text))

Max Activating Token Index: 787