Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1251 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1464567 (Python Code)

Max Activating Token Index: 862

Text #1

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1641895 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1464906 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2690. Min Act: -0.0000

Data Index: 1561689 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1495623 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2969. Min Act: -0.0000

Data Index: 1480111 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1523298 (Python Code)

Max Activating Token Index: 269

Text #7

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1463746 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1643895 (Python Code)

Max Activating Token Index: 653

Text #9

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1458087 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1521301 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1398460 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1512094 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1610. Min Act: -0.0000

Data Index: 1366364 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1396165 (Python Code)

Max Activating Token Index: 564

Text #15

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1422097 (Python Code)

Max Activating Token Index: 191

Text #16

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1535769 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1601687 (Python Code)

Max Activating Token Index: 839

Text #18

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1616706 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 1.5404. Min Range: -1.5404

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1541484 (Python Code)

Max Activating Token Index: 299