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

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

Neuron 4292 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7586. Min Act: -0.0001

Data Index: 1530177 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1590277 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1455369 (Python Code)

Max Activating Token Index: 720

Text #3

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.7275. Min Act: -0.0001

Data Index: 1598595 (Python Code)

Max Activating Token Index: 413

Text #4

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1535114 (Python Code)

Max Activating Token Index: 655

Text #5

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6812. Min Act: -0.0001

Data Index: 1376553 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6374. Min Act: -0.0001

Data Index: 1515890 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1645322 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1496714 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1645591 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1494277 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6081. Min Act: -0.0001

Data Index: 1412335 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1652896 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1476613 (Python Code)

Max Activating Token Index: 620

Text #14

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1539885 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1485328 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1632860 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1632444 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5739. Min Act: -0.0001

Data Index: 1495477 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.7586. Min Range: -0.7586

Max Act: 0.5606. Min Act: -0.0001

Data Index: 1644565 (Python Code)

Max Activating Token Index: 680