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

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

Neuron 2704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.2664. Min Act: -0.0000

Data Index: 1440042 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1709. Min Act: -0.0000

Data Index: 1404670 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0032. Min Act: -0.0000

Data Index: 1588392 (Python Code)

Max Activating Token Index: 241

Text #3

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1420. Min Act: -0.0000

Data Index: 1630226 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1408. Min Act: -0.0000

Data Index: 1602604 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0638. Min Act: -0.0000

Data Index: 1536202 (Python Code)

Max Activating Token Index: 703

Text #6

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.7811. Min Act: -0.0000

Data Index: 1395574 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.9191. Min Act: -0.0000

Data Index: 1592453 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.5888. Min Act: -0.0000

Data Index: 1595192 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.9722. Min Act: -0.0000

Data Index: 1482866 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.7756. Min Act: -0.0000

Data Index: 1584392 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.8794. Min Act: -0.0000

Data Index: 1580300 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1412474 (Python Code)

Max Activating Token Index: 842

Text #13

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.5842. Min Act: -0.0000

Data Index: 1651988 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.6782. Min Act: -0.0000

Data Index: 1571483 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.6650. Min Act: -0.0000

Data Index: 1494130 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.6256. Min Act: -0.0000

Data Index: 1554251 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1597036 (Python Code)

Max Activating Token Index: 448

Text #18

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.4725. Min Act: -0.0000

Data Index: 1422019 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 3.2664. Min Range: -3.2664

Max Act: 2.4625. Min Act: -0.0000

Data Index: 1621277 (Python Code)

Max Activating Token Index: 475