Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1012725 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2233. Min Act: -0.0000

Data Index: 12551 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2088. Min Act: -0.0000

Data Index: 555495 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1989. Min Act: -0.0000

Data Index: 140594 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2058. Min Act: -0.0001

Data Index: 115774 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1862. Min Act: -0.0000

Data Index: 322924 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1905. Min Act: -0.0000

Data Index: 524861 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.2029. Min Act: -0.0001

Data Index: 802519 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1817. Min Act: -0.0000

Data Index: 213898 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1722. Min Act: -0.0000

Data Index: 520320 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1775. Min Act: -0.0000

Data Index: 794393 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1653. Min Act: -0.0000

Data Index: 231407 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1570. Min Act: -0.0000

Data Index: 383021 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1556. Min Act: -0.0000

Data Index: 407901 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1597. Min Act: -0.0000

Data Index: 685984 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1524. Min Act: -0.0001

Data Index: 230325 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1385. Min Act: -0.0001

Data Index: 565378 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1420. Min Act: -0.0000

Data Index: 224915 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1464. Min Act: -0.0000

Data Index: 497673 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.2233. Min Range: -0.2233

Max Act: 0.1269. Min Act: -0.0001

Data Index: 332396 (C4 (Web Text))

Max Activating Token Index: 1023