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

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

Neuron 837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1053198 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 298714 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 713732 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1636520 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 176321 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1402407 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1612419 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1067411 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 814662 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 111267 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 181405 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1515335 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: -0.0000. Min Act: -0.0003

Data Index: 757857 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: -0.0000. Min Act: -0.0002

Data Index: 263926 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 227457 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1172329 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 743135 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0000. Min Act: -0.0002

Data Index: 233824 (C4 (Web Text))

Max Activating Token Index: 47