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

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

Neuron 3531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.2691. Min Act: -0.0000

Data Index: 1370992 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1551525 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1491171 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1425992 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1511620 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.4878. Min Act: -0.0000

Data Index: 1493466 (Python Code)

Max Activating Token Index: 590

Text #6

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1400465 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1478660 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1495957 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.4346. Min Act: -0.0000

Data Index: 1405035 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1641254 (Python Code)

Max Activating Token Index: 873

Text #11

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1487895 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1588546 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1628900 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1638624 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1450793 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.3077. Min Act: -0.0000

Data Index: 1380677 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1435607 (Python Code)

Max Activating Token Index: 735

Text #18

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1511421 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1639851 (Python Code)

Max Activating Token Index: 485