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

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

Neuron 800 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: 0.7040. Min Range: -0.7040

Max Act: 0.6924. Min Act: -0.0000

Data Index: 264657 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.7040. Min Act: -0.0000

Data Index: 989342 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.7006. Min Act: -0.0000

Data Index: 244278 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1258093 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6558. Min Act: 0.0000

Data Index: 373491 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6480. Min Act: -0.0000

Data Index: 876629 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1114755 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6302. Min Act: -0.0000

Data Index: 393015 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6234. Min Act: -0.0000

Data Index: 246428 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6191. Min Act: 0.0000

Data Index: 849200 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6189. Min Act: -0.0000

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6089. Min Act: -0.0000

Data Index: 467814 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1159943 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5823. Min Act: -0.0000

Data Index: 709554 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1186006 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5635. Min Act: -0.0000

Data Index: 141030 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6017. Min Act: -0.0000

Data Index: 898439 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5769. Min Act: -0.0000

Data Index: 244926 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5730. Min Act: -0.0000

Data Index: 369101 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5743. Min Act: -0.0000

Data Index: 126502 (C4 (Web Text))

Max Activating Token Index: 875