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

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

Neuron 4052 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9874. Min Act: -0.0000

Data Index: 677322 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9555. Min Act: 0.0000

Data Index: 490482 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9945. Min Act: 0.0001

Data Index: 851005 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7476. Min Act: -0.0000

Data Index: 517906 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7435. Min Act: 0.0001

Data Index: 749138 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7412. Min Act: 0.0001

Data Index: 1203683 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7062. Min Act: -0.0000

Data Index: 377390 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7510. Min Act: -0.0000

Data Index: 600353 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7077. Min Act: 0.0000

Data Index: 352890 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7528. Min Act: -0.0000

Data Index: 831035 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6949. Min Act: -0.0000

Data Index: 422024 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6862. Min Act: -0.0000

Data Index: 2789 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6751. Min Act: -0.0000

Data Index: 322094 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6918. Min Act: -0.0000

Data Index: 270580 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6678. Min Act: 0.0000

Data Index: 31917 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7064. Min Act: -0.0000

Data Index: 355940 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6760. Min Act: 0.0001

Data Index: 250815 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6511. Min Act: -0.0000

Data Index: 566959 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6679. Min Act: -0.0000

Data Index: 987129 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6442. Min Act: 0.0001

Data Index: 561894 (C4 (Web Text))

Max Activating Token Index: 32