Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1493. Min Range: -3.1493

Max Act: 3.1493. Min Act: -0.0000

Data Index: 241013 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.9071. Min Act: -0.0000

Data Index: 342517 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.9826. Min Act: -0.0000

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.7824. Min Act: -0.0000

Data Index: 317048 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.7803. Min Act: -0.0000

Data Index: 449604 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5315. Min Act: -0.0000

Data Index: 954242 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.6162. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.4558. Min Act: -0.0000

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5923. Min Act: -0.0000

Data Index: 32642 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5649. Min Act: -0.0000

Data Index: 262375 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5608. Min Act: -0.0000

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.4651. Min Act: -0.0000

Data Index: 730413 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5709. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.2772. Min Act: -0.0000

Data Index: 809313 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.5046. Min Act: -0.0000

Data Index: 605370 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.2348. Min Act: -0.0000

Data Index: 731470 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.2182. Min Act: -0.0000

Data Index: 693262 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.3220. Min Act: -0.0000

Data Index: 109592 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.1493. Min Range: -3.1493

Max Act: 2.1695. Min Act: -0.0000

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.1493. Min Range: -3.1493

Max Act: 1.9889. Min Act: -0.0000

Data Index: 653280 (C4 (Web Text))

Max Activating Token Index: 855