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

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

Neuron 77 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1340696 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1332714 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0734. Min Act: -0.0000

Data Index: 633731 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1653955 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9957. Min Act: -0.0000

Data Index: 446378 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1494916 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1477688 (Python Code)

Max Activating Token Index: 341

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9934. Min Act: -0.0000

Data Index: 448221 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0042. Min Act: -0.0000

Data Index: 49974 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1369563 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1542375 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1511939 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8814. Min Act: -0.0000

Data Index: 193132 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8916. Min Act: -0.0000

Data Index: 896209 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1535842 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9108. Min Act: -0.0000

Data Index: 146987 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1057427 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8926. Min Act: -0.0000

Data Index: 24483 (C4 (Web Text))

Max Activating Token Index: 245