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

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

Neuron 3696 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1852. Min Act: -0.0000

Data Index: 1005584 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1433. Min Act: -0.0000

Data Index: 766021 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.9694. Min Act: -0.0000

Data Index: 156502 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.7289. Min Act: -0.0000

Data Index: 339492 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1175422 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.5822. Min Act: -0.0000

Data Index: 229594 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.5735. Min Act: -0.0000

Data Index: 275112 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.5483. Min Act: -0.0000

Data Index: 1217222 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.3109. Min Act: -0.0000

Data Index: 818516 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.4998. Min Act: -0.0000

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.3588. Min Act: -0.0000

Data Index: 1056608 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.4760. Min Act: -0.0000

Data Index: 1205735 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1006171 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1092796 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.3457. Min Act: -0.0000

Data Index: 720902 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.3457. Min Act: -0.0000

Data Index: 1270165 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.2118. Min Act: -0.0000

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.2208. Min Act: -0.0000

Data Index: 40027 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.4693. Min Act: -0.0000

Data Index: 243823 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.1852. Min Range: -3.1852

Max Act: 2.3202. Min Act: -0.0000

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 807