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

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

Neuron 5064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1341. Min Range: -1.1341

Max Act: 1.1341. Min Act: -0.0002

Data Index: 1038495 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8274. Min Act: -0.0002

Data Index: 1261036 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8209. Min Act: -0.0002

Data Index: 1267059 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7707. Min Act: -0.0002

Data Index: 349484 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6023. Min Act: -0.0002

Data Index: 310613 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.9357. Min Act: -0.0002

Data Index: 404785 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7361. Min Act: -0.0002

Data Index: 117644 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.8229. Min Act: -0.0002

Data Index: 400538 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6915. Min Act: -0.0002

Data Index: 300647 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7050. Min Act: -0.0002

Data Index: 941908 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7155. Min Act: -0.0002

Data Index: 1336125 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5263. Min Act: -0.0002

Data Index: 1015565 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6761. Min Act: -0.0002

Data Index: 1237178 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6133. Min Act: -0.0002

Data Index: 875619 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6721. Min Act: -0.0002

Data Index: 654105 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6723. Min Act: -0.0002

Data Index: 790046 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6846. Min Act: -0.0002

Data Index: 325015 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.6005. Min Act: -0.0002

Data Index: 1147511 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.5113. Min Act: -0.0002

Data Index: 336526 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.1341. Min Range: -1.1341

Max Act: 0.7007. Min Act: -0.0002

Data Index: 807883 (C4 (Web Text))

Max Activating Token Index: 374