Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.8093. Min Act: -0.0001

Data Index: 501418 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.7601. Min Act: -0.0000

Data Index: 638439 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.7298. Min Act: -0.0000

Data Index: 992616 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1020546 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1348103 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6306. Min Act: -0.0001

Data Index: 716232 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5846. Min Act: -0.0000

Data Index: 677733 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5883. Min Act: -0.0001

Data Index: 1161919 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6636. Min Act: -0.0000

Data Index: 166281 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1046776 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1346366 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6024. Min Act: -0.0000

Data Index: 423251 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5774. Min Act: -0.0000

Data Index: 972846 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1265240 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5848. Min Act: -0.0000

Data Index: 129652 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5824. Min Act: -0.0000

Data Index: 445459 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5720. Min Act: -0.0001

Data Index: 723988 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5743. Min Act: -0.0001

Data Index: 375917 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5720. Min Act: -0.0001

Data Index: 348913 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5581. Min Act: -0.0001

Data Index: 617295 (C4 (Web Text))

Max Activating Token Index: 589