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

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

Neuron 1360 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: 0.2144. Min Range: -0.2144

Max Act: 0.2144. Min Act: -0.0003

Data Index: 1148156 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2015. Min Act: -0.0002

Data Index: 130562 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2041. Min Act: -0.0003

Data Index: 1000048 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1969. Min Act: -0.0003

Data Index: 387032 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.2017. Min Act: -0.0003

Data Index: 556288 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1930. Min Act: -0.0003

Data Index: 1205052 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1851. Min Act: -0.0003

Data Index: 628849 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1969. Min Act: -0.0003

Data Index: 1151719 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1811. Min Act: -0.0003

Data Index: 408305 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1872. Min Act: -0.0003

Data Index: 217505 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1877. Min Act: -0.0003

Data Index: 326575 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1773. Min Act: -0.0003

Data Index: 690660 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1815. Min Act: -0.0002

Data Index: 395658 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1792. Min Act: -0.0003

Data Index: 980477 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1949. Min Act: -0.0003

Data Index: 1292888 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1980. Min Act: -0.0003

Data Index: 32701 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1724. Min Act: -0.0003

Data Index: 109892 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1706. Min Act: -0.0003

Data Index: 28350 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1702. Min Act: -0.0003

Data Index: 1250310 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.2144. Min Range: -0.2144

Max Act: 0.1635. Min Act: -0.0003

Data Index: 232766 (C4 (Web Text))

Max Activating Token Index: 42