Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1567062 (Python Code)

Max Activating Token Index: 524

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1598268 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1597631 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1566531 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1630329 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1482811 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1644340 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1583. Min Act: 0.0000

Data Index: 624863 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1675. Min Act: -0.0001

Data Index: 408892 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1556. Min Act: -0.0000

Data Index: 450895 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1615571 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1397239 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1654. Min Act: -0.0001

Data Index: 663256 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1492. Min Act: 0.0001

Data Index: 387442 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1473. Min Act: -0.0000

Data Index: 336674 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1443238 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1467253 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1427. Min Act: 0.0001

Data Index: 971370 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1474. Min Act: -0.0001

Data Index: 184796 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.1510. Min Act: -0.0000

Data Index: 54686 (C4 (Web Text))

Max Activating Token Index: 203