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

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

Neuron 932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.7603. Min Act: -0.0001

Data Index: 274552 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6784. Min Act: -0.0001

Data Index: 351533 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6789. Min Act: -0.0001

Data Index: 1284437 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6932. Min Act: -0.0001

Data Index: 1307969 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6292. Min Act: -0.0001

Data Index: 825509 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6680. Min Act: -0.0000

Data Index: 457213 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5446. Min Act: -0.0001

Data Index: 1443310 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5740. Min Act: -0.0001

Data Index: 276474 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5304. Min Act: -0.0001

Data Index: 695732 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6011. Min Act: -0.0001

Data Index: 599665 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5501. Min Act: -0.0001

Data Index: 151849 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5478. Min Act: -0.0001

Data Index: 553387 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6257. Min Act: -0.0001

Data Index: 366076 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5055. Min Act: -0.0001

Data Index: 859993 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.6212. Min Act: -0.0001

Data Index: 779289 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5304. Min Act: -0.0001

Data Index: 149527 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5128. Min Act: -0.0001

Data Index: 528613 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4722. Min Act: -0.0001

Data Index: 66550 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.5167. Min Act: -0.0001

Data Index: 155671 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.7603. Min Range: -1.7603

Max Act: 1.4685. Min Act: -0.0001

Data Index: 1652363 (Python Code)

Max Activating Token Index: 184