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

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

Neuron 4444 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0002

Data Index: 922007 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2062. Min Act: -0.0002

Data Index: 311432 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2005. Min Act: -0.0002

Data Index: 46192 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2180. Min Act: -0.0002

Data Index: 1107496 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1532. Min Act: -0.0002

Data Index: 701352 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2047. Min Act: -0.0002

Data Index: 624458 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1782. Min Act: -0.0002

Data Index: 521690 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2033. Min Act: -0.0002

Data Index: 427655 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2096. Min Act: -0.0002

Data Index: 346291 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1894. Min Act: -0.0002

Data Index: 678310 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1890. Min Act: -0.0002

Data Index: 351916 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1992. Min Act: -0.0002

Data Index: 1419482 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1896. Min Act: -0.0002

Data Index: 1348168 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1858. Min Act: -0.0002

Data Index: 1202192 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1817. Min Act: -0.0002

Data Index: 9322 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1803. Min Act: -0.0002

Data Index: 985967 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1859. Min Act: -0.0002

Data Index: 677614 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1781. Min Act: -0.0002

Data Index: 27730 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1688. Min Act: -0.0002

Data Index: 356760 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1777. Min Act: -0.0002

Data Index: 717523 (C4 (Web Text))

Max Activating Token Index: 4