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

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

Neuron 2018 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.3044. Min Act: -0.0003

Data Index: 1531 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2992. Min Act: -0.0002

Data Index: 1140327 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2696. Min Act: -0.0002

Data Index: 167238 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2711. Min Act: -0.0003

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2533. Min Act: -0.0002

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2657. Min Act: -0.0003

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2617. Min Act: -0.0002

Data Index: 653139 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2471. Min Act: -0.0003

Data Index: 1312120 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2525. Min Act: -0.0002

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1104146 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2290. Min Act: -0.0003

Data Index: 1310919 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2265. Min Act: -0.0002

Data Index: 1302041 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2180. Min Act: -0.0002

Data Index: 721706 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2103. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.1958. Min Act: -0.0002

Data Index: 47530 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2013. Min Act: -0.0002

Data Index: 774408 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1078289 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.1887. Min Act: -0.0002

Data Index: 289997 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.1859. Min Act: -0.0002

Data Index: 845846 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.3044. Min Range: -0.3044

Max Act: 0.1794. Min Act: -0.0002

Data Index: 146813 (C4 (Web Text))

Max Activating Token Index: 661