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

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

Neuron 553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0253. Min Range: -2.0253

Max Act: 2.0253. Min Act: -0.0000

Data Index: 1375249 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1651485 (Python Code)

Max Activating Token Index: 769

Text #2

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.7703. Min Act: -0.0000

Data Index: 1462659 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.7712. Min Act: -0.0000

Data Index: 1438121 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1621697 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5910. Min Act: -0.0000

Data Index: 1635789 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1639392 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1581726 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1598580 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1363344 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5021. Min Act: -0.0000

Data Index: 1631013 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5710. Min Act: -0.0000

Data Index: 1525680 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1461732 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1399762 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1586062 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1447491 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1470555 (Python Code)

Max Activating Token Index: 730

Text #17

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1614945 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1632955 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1573541 (Python Code)

Max Activating Token Index: 333