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

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

Neuron 819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1035836 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0994. Min Act: -0.0003

Data Index: 944847 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1177624 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0940. Min Act: -0.0003

Data Index: 1167852 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0852. Min Act: -0.0003

Data Index: 1253262 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0815. Min Act: -0.0003

Data Index: 365367 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0783. Min Act: -0.0003

Data Index: 188110 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1351533 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0897. Min Act: -0.0003

Data Index: 918375 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0826. Min Act: -0.0003

Data Index: 635472 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1176454 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0853. Min Act: -0.0003

Data Index: 396903 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0765. Min Act: -0.0003

Data Index: 1043512 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1009463 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1328300 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0777. Min Act: -0.0003

Data Index: 919804 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1149655 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0826. Min Act: -0.0003

Data Index: 100133 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1053608 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0720. Min Act: -0.0003

Data Index: 509782 (C4 (Web Text))

Max Activating Token Index: 436