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

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

Neuron 2814 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1079061 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.4772. Min Act: -0.0000

Data Index: 598181 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.4084. Min Act: -0.0000

Data Index: 710483 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2552. Min Act: -0.0000

Data Index: 784454 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1045390 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2089. Min Act: -0.0000

Data Index: 201736 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.1727. Min Act: -0.0000

Data Index: 188526 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2328. Min Act: -0.0000

Data Index: 400061 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2323. Min Act: -0.0000

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1205780 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.1113. Min Act: -0.0000

Data Index: 981226 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1339747 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0828. Min Act: -0.0000

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.1282. Min Act: -0.0000

Data Index: 855389 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1248815 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0284. Min Act: -0.0000

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0581. Min Act: -0.0000

Data Index: 584106 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0388. Min Act: -0.0000

Data Index: 768670 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.5064. Min Range: -1.5064

Max Act: 1.0603. Min Act: -0.0000

Data Index: 438281 (C4 (Web Text))

Max Activating Token Index: 265