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

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

Neuron 4078 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9874. Min Act: -0.0000

Data Index: 438402 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1285865 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1304027 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7952. Min Act: -0.0000

Data Index: 917821 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7782. Min Act: -0.0000

Data Index: 504542 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1031171 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1123103 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7978. Min Act: -0.0000

Data Index: 646760 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7643. Min Act: -0.0000

Data Index: 747017 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7265. Min Act: -0.0000

Data Index: 848219 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7666. Min Act: -0.0000

Data Index: 341441 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7769. Min Act: -0.0000

Data Index: 959380 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7484. Min Act: -0.0000

Data Index: 19488 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1154867 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7345. Min Act: -0.0000

Data Index: 142241 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7237. Min Act: -0.0000

Data Index: 989442 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1180766 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7104. Min Act: -0.0000

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.6674. Min Act: -0.0000

Data Index: 957306 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.7021. Min Act: -0.0000

Data Index: 575060 (C4 (Web Text))

Max Activating Token Index: 249