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

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

Neuron 4542 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: 1.5637. Min Range: -1.5637

Max Act: 1.5637. Min Act: -0.0001

Data Index: 1616265 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.5037. Min Act: -0.0001

Data Index: 1447452 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4563. Min Act: -0.0001

Data Index: 1538889 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4286. Min Act: -0.0001

Data Index: 1605337 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4440. Min Act: -0.0001

Data Index: 1415828 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.4075. Min Act: -0.0001

Data Index: 1478589 (Python Code)

Max Activating Token Index: 918

Text #6

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3888. Min Act: -0.0001

Data Index: 1572511 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3212. Min Act: -0.0001

Data Index: 1414878 (Python Code)

Max Activating Token Index: 550

Text #8

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3604. Min Act: -0.0001

Data Index: 1496569 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3306. Min Act: -0.0001

Data Index: 1407018 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2669. Min Act: -0.0001

Data Index: 1597674 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3166. Min Act: -0.0001

Data Index: 1390621 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1566241 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.1905. Min Act: -0.0001

Data Index: 1656474 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2919. Min Act: -0.0001

Data Index: 1630040 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2952. Min Act: -0.0001

Data Index: 1647121 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2752. Min Act: -0.0001

Data Index: 1498471 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2130. Min Act: -0.0001

Data Index: 1459523 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2213. Min Act: -0.0001

Data Index: 1612590 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.2436. Min Act: -0.0001

Data Index: 1598370 (Python Code)

Max Activating Token Index: 1019