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

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

Neuron 4010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0838. Min Range: -1.0838

Max Act: 1.0838. Min Act: -0.0000

Data Index: 454784 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8981. Min Act: -0.0000

Data Index: 727267 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.9004. Min Act: -0.0000

Data Index: 242049 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8490. Min Act: -0.0000

Data Index: 741291 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8476. Min Act: -0.0000

Data Index: 322240 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.8446. Min Act: -0.0000

Data Index: 737556 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7359. Min Act: -0.0000

Data Index: 287314 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1336530 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1263832 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6787. Min Act: -0.0000

Data Index: 654886 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1349978 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1268088 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6163. Min Act: -0.0000

Data Index: 978176 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6479. Min Act: -0.0000

Data Index: 990895 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6269. Min Act: -0.0000

Data Index: 482560 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6052. Min Act: -0.0000

Data Index: 164234 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1517884 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6013. Min Act: -0.0000

Data Index: 215250 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.6368. Min Act: -0.0000

Data Index: 71278 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.0838. Min Range: -1.0838

Max Act: 0.5773. Min Act: -0.0000

Data Index: 282817 (C4 (Web Text))

Max Activating Token Index: 424