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

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

Neuron 4602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.1510. Min Act: 0.0001

Data Index: 1592065 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1607733 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1539378 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.1447. Min Act: 0.0000

Data Index: 1633348 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.1012. Min Act: 0.0002

Data Index: 1548641 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1266264 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1404828 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.1510. Min Range: -1.1510

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1617161 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1540626 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9869. Min Act: 0.0002

Data Index: 1525437 (Python Code)

Max Activating Token Index: 534

Text #10

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1412866 (Python Code)

Max Activating Token Index: 857

Text #11

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1393120 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1552536 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1537154 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1530665 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1588715 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1529293 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.8404. Min Act: 0.0002

Data Index: 1369406 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.8630. Min Act: 0.0002

Data Index: 1591702 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 1.1510. Min Range: -1.1510

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1653230 (Python Code)

Max Activating Token Index: 879