Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1364002 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1362221 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1367289 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1551333 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1564533 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1506. Min Act: -0.0001

Data Index: 942878 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1450734 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1621252 (Python Code)

Max Activating Token Index: 342

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1540518 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1621333 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1587536 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1360198 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1389398 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1468601 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1527792 (Python Code)

Max Activating Token Index: 457

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1654578 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1535006 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1530480 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1528765 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1449323 (Python Code)

Max Activating Token Index: 781