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

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

Neuron 4862 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1109606 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.1148. Min Act: -0.0000

Data Index: 755390 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0206. Min Act: -0.0000

Data Index: 978650 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9843. Min Act: -0.0000

Data Index: 752072 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9851. Min Act: -0.0000

Data Index: 53619 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1240640 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.1848. Min Range: -1.1848

Max Act: 1.0106. Min Act: -0.0000

Data Index: 285061 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9852. Min Act: -0.0000

Data Index: 401025 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1216061 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9804. Min Act: -0.0000

Data Index: 97466 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9597. Min Act: -0.0000

Data Index: 544539 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8981. Min Act: -0.0000

Data Index: 647056 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9055. Min Act: -0.0000

Data Index: 500761 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.9430. Min Act: -0.0000

Data Index: 729889 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8995. Min Act: -0.0000

Data Index: 736853 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8765. Min Act: -0.0000

Data Index: 766687 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8500. Min Act: -0.0000

Data Index: 568328 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8773. Min Act: -0.0000

Data Index: 989211 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8193. Min Act: -0.0000

Data Index: 624748 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.1848. Min Range: -1.1848

Max Act: 0.8423. Min Act: -0.0000

Data Index: 269840 (C4 (Web Text))

Max Activating Token Index: 315