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

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

Neuron 1971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0002

Data Index: 388550 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0833. Min Act: -0.0002

Data Index: 466379 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0808. Min Act: -0.0002

Data Index: 9587 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0771. Min Act: -0.0002

Data Index: 930013 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0715. Min Act: -0.0002

Data Index: 210644 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0679. Min Act: -0.0002

Data Index: 371152 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0688. Min Act: -0.0002

Data Index: 42964 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0687. Min Act: -0.0002

Data Index: 650706 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1360773 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0672. Min Act: -0.0002

Data Index: 683904 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0664. Min Act: -0.0002

Data Index: 733356 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0657. Min Act: -0.0002

Data Index: 810121 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0637. Min Act: -0.0002

Data Index: 155937 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1053282 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1271773 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1440858 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0623. Min Act: -0.0002

Data Index: 756427 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0598. Min Act: -0.0002

Data Index: 139318 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0598. Min Act: -0.0002

Data Index: 179560 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1038826 (C4 (Web Text))

Max Activating Token Index: 129