Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2808 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2217. Min Act: -0.0000

Data Index: 80947 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1254315 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2011. Min Act: -0.0000

Data Index: 422157 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2048. Min Act: -0.0000

Data Index: 129857 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1950. Min Act: -0.0000

Data Index: 627783 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1178852 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1907. Min Act: -0.0000

Data Index: 565196 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1894. Min Act: -0.0000

Data Index: 385211 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1880. Min Act: -0.0001

Data Index: 602597 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1871. Min Act: -0.0001

Data Index: 470187 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1870. Min Act: -0.0000

Data Index: 538262 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1759. Min Act: -0.0000

Data Index: 723515 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1096138 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1213231 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1653. Min Act: -0.0000

Data Index: 831011 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1648. Min Act: -0.0000

Data Index: 220836 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1640. Min Act: -0.0000

Data Index: 539569 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1163437 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1677. Min Act: -0.0000

Data Index: 272613 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1010609 (C4 (Web Text))

Max Activating Token Index: 758