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

Dataset: The Pile

Neuron 778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1190. Min Act: -0.0000

Data Index: 986038 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1035165 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1847978 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0963. Min Act: -0.0000

Data Index: 703110 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1533816 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0934. Min Act: -0.0000

Data Index: 644494 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0900. Min Act: -0.0000

Data Index: 592715 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1571765 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1865440 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1636410 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0864. Min Act: -0.0000

Data Index: 612763 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1023141 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0890. Min Act: -0.0000

Data Index: 726345 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0879. Min Act: -0.0000

Data Index: 440351 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0846. Min Act: -0.0000

Data Index: 201122 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1940410 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1626186 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1473169 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0829. Min Act: -0.0000

Data Index: 899641 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0855. Min Act: -0.0000

Data Index: 674461 (The Pile)

Max Activating Token Index: 430