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

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

Neuron 347 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0822. Min Range: -2.0822

Max Act: 2.0822. Min Act: -0.0000

Data Index: 1294296 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.9142. Min Act: -0.0000

Data Index: 235792 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.9550. Min Act: -0.0000

Data Index: 921212 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.8998. Min Act: -0.0000

Data Index: 644423 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6573. Min Act: -0.0000

Data Index: 1207334 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.7189. Min Act: -0.0000

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6058. Min Act: -0.0000

Data Index: 5562 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6059. Min Act: -0.0000

Data Index: 1137997 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1266442 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5148. Min Act: -0.0000

Data Index: 917582 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1264984 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.4781. Min Act: -0.0000

Data Index: 1617894 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.4871. Min Act: -0.0000

Data Index: 778177 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5669. Min Act: -0.0000

Data Index: 851002 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1206627 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5536. Min Act: -0.0000

Data Index: 563486 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1014943 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5317. Min Act: -0.0000

Data Index: 173528 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.5739. Min Act: -0.0000

Data Index: 149457 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.0822. Min Range: -2.0822

Max Act: 1.4703. Min Act: -0.0000

Data Index: 834565 (C4 (Web Text))

Max Activating Token Index: 555