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

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

Neuron 1681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.1010. Min Act: -0.0000

Data Index: 293131 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 2.1010. Min Range: -2.1010

Max Act: 2.0000. Min Act: -0.0000

Data Index: 1309550 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1215370 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1278596 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.5121. Min Act: -0.0000

Data Index: 48315 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.6793. Min Act: -0.0000

Data Index: 625714 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.4506. Min Act: -0.0000

Data Index: 1547 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.4951. Min Act: -0.0000

Data Index: 374012 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3962. Min Act: -0.0000

Data Index: 66573 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1176512 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.4423. Min Act: -0.0000

Data Index: 449794 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1088055 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3718. Min Act: -0.0000

Data Index: 516978 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.2437. Min Act: -0.0000

Data Index: 434430 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3371. Min Act: -0.0000

Data Index: 952739 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1157210 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3509. Min Act: -0.0000

Data Index: 998402 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.2931. Min Act: -0.0000

Data Index: 920791 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.3258. Min Act: -0.0000

Data Index: 611451 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 2.1010. Min Range: -2.1010

Max Act: 1.2918. Min Act: -0.0000

Data Index: 473912 (C4 (Web Text))

Max Activating Token Index: 959