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

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

Neuron 821 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.5048. Min Act: -0.0000

Data Index: 1482964 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1019694 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.4012. Min Act: -0.0000

Data Index: 1595899 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.3410. Min Act: -0.0000

Data Index: 1438056 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2980. Min Act: -0.0000

Data Index: 1576646 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1982. Min Act: -0.0000

Data Index: 1478869 (Python Code)

Max Activating Token Index: 932

Text #6

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1637549 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1590. Min Act: -0.0000

Data Index: 1553452 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2154. Min Act: -0.0000

Data Index: 140964 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2129. Min Act: -0.0000

Data Index: 426336 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1698. Min Act: -0.0000

Data Index: 622318 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1175. Min Act: -0.0000

Data Index: 1303528 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1156. Min Act: -0.0000

Data Index: 364427 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1985. Min Act: -0.0000

Data Index: 391259 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.0790. Min Act: -0.0000

Data Index: 172032 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2398. Min Act: -0.0000

Data Index: 1577311 (Python Code)

Max Activating Token Index: 884

Text #16

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.2157. Min Act: -0.0000

Data Index: 1498482 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1465883 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 2.5392. Min Range: -2.5392

Max Act: 1.9952. Min Act: -0.0000

Data Index: 17698 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 2.5392. Min Range: -2.5392

Max Act: 2.0256. Min Act: -0.0000

Data Index: 1538846 (Python Code)

Max Activating Token Index: 85