Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1041 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2247. Min Act: -0.0003

Data Index: 42846 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2335. Min Act: -0.0003

Data Index: 809616 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2289. Min Act: -0.0003

Data Index: 1233242 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2230. Min Act: -0.0003

Data Index: 1255120 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2134. Min Act: -0.0004

Data Index: 579273 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2294. Min Act: -0.0004

Data Index: 647220 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2171. Min Act: -0.0004

Data Index: 671008 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2096. Min Act: -0.0003

Data Index: 236384 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2113. Min Act: -0.0003

Data Index: 314329 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2044. Min Act: -0.0003

Data Index: 170037 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2022. Min Act: -0.0003

Data Index: 1245409 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2010. Min Act: -0.0003

Data Index: 1357690 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1996. Min Act: -0.0003

Data Index: 433250 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.2043. Min Act: -0.0003

Data Index: 1003294 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1996. Min Act: -0.0003

Data Index: 941581 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1933. Min Act: -0.0003

Data Index: 57644 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1939. Min Act: -0.0003

Data Index: 1351306 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1881. Min Act: -0.0004

Data Index: 636840 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1854. Min Act: -0.0003

Data Index: 474418 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.2335. Min Range: -0.2335

Max Act: 0.1878. Min Act: -0.0003

Data Index: 1253430 (C4 (Web Text))

Max Activating Token Index: 985