Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1577. Min Act: -0.0001

Data Index: 201622 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1456. Min Act: -0.0001

Data Index: 845401 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1308. Min Act: -0.0001

Data Index: 400409 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1184. Min Act: -0.0001

Data Index: 384005 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1188. Min Act: -0.0001

Data Index: 337891 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1180. Min Act: -0.0001

Data Index: 938147 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1000492 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1332032 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1027. Min Act: -0.0001

Data Index: 564010 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1144. Min Act: -0.0001

Data Index: 392941 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1121. Min Act: -0.0001

Data Index: 763717 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1090. Min Act: -0.0001

Data Index: 358342 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.0959. Min Act: -0.0001

Data Index: 584445 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1037. Min Act: -0.0001

Data Index: 328685 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1065. Min Act: -0.0001

Data Index: 675758 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1015. Min Act: -0.0001

Data Index: 738533 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1035. Min Act: -0.0001

Data Index: 535061 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1042. Min Act: -0.0001

Data Index: 664610 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1076. Min Act: -0.0001

Data Index: 756462 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1577. Min Range: -0.1577

Max Act: 0.1029. Min Act: -0.0001

Data Index: 88250 (C4 (Web Text))

Max Activating Token Index: 260