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

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

Neuron 6095 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: 1.2184. Min Range: -1.2184

Max Act: 1.1940. Min Act: -0.0000

Data Index: 229138 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1836. Min Act: -0.0000

Data Index: 483620 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1141468 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1814. Min Act: -0.0000

Data Index: 532798 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0589. Min Act: -0.0000

Data Index: 913318 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0497. Min Act: -0.0000

Data Index: 92677 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1350. Min Act: -0.0000

Data Index: 643972 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1301336 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1134. Min Act: -0.0000

Data Index: 61441 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1158. Min Act: -0.0000

Data Index: 478536 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0320. Min Act: -0.0000

Data Index: 649180 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1013. Min Act: -0.0000

Data Index: 728985 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0699. Min Act: -0.0000

Data Index: 409427 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1261. Min Act: -0.0000

Data Index: 707411 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1787. Min Act: -0.0000

Data Index: 387068 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1278762 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1555. Min Act: -0.0000

Data Index: 847164 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1071. Min Act: -0.0000

Data Index: 793705 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0845. Min Act: -0.0000

Data Index: 556606 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1116. Min Act: -0.0000

Data Index: 750814 (C4 (Web Text))

Max Activating Token Index: 654