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

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

Neuron 1179 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: 1.8219. Min Range: -1.8219

Max Act: 1.8219. Min Act: -0.0000

Data Index: 1328180 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.7344. Min Act: -0.0000

Data Index: 948525 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1341386 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1198080 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.6477. Min Act: -0.0000

Data Index: 704612 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1138382 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1283113 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.4301. Min Act: -0.0000

Data Index: 253246 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.3525. Min Act: -0.0000

Data Index: 130714 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.3613. Min Act: -0.0000

Data Index: 140672 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.4122. Min Act: -0.0000

Data Index: 260132 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.3626. Min Act: -0.0000

Data Index: 38513 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.3649. Min Act: -0.0000

Data Index: 951250 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2922. Min Act: -0.0000

Data Index: 908576 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1243427 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.1835. Min Act: -0.0000

Data Index: 361029 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2590. Min Act: -0.0000

Data Index: 85297 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2474. Min Act: -0.0000

Data Index: 568731 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2170. Min Act: -0.0000

Data Index: 78092 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.8219. Min Range: -1.8219

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1070395 (C4 (Web Text))

Max Activating Token Index: 977