Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5680 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1123542 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5827. Min Act: -0.0000

Data Index: 342972 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5744. Min Act: -0.0000

Data Index: 647237 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1063940 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4931. Min Act: -0.0000

Data Index: 946285 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5445. Min Act: -0.0000

Data Index: 85542 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1043184 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1161773 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4796. Min Act: -0.0000

Data Index: 425015 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5055. Min Act: -0.0000

Data Index: 425249 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5164. Min Act: 0.0000

Data Index: 1278712 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4565. Min Act: -0.0000

Data Index: 227628 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4429. Min Act: -0.0000

Data Index: 657528 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4812. Min Act: -0.0000

Data Index: 890968 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4625. Min Act: -0.0000

Data Index: 511979 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4464. Min Act: -0.0000

Data Index: 38303 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4220. Min Act: -0.0000

Data Index: 849480 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4510. Min Act: -0.0000

Data Index: 207234 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4386. Min Act: 0.0000

Data Index: 35750 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4400. Min Act: 0.0001

Data Index: 857426 (C4 (Web Text))

Max Activating Token Index: 684