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

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

Neuron 3076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2857. Min Act: -0.0000

Data Index: 563584 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2481. Min Act: -0.0000

Data Index: 534891 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1288992 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2204. Min Act: -0.0000

Data Index: 2107 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2192. Min Act: -0.0000

Data Index: 903731 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2019. Min Act: -0.0000

Data Index: 626877 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1113223 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1841. Min Act: -0.0000

Data Index: 365037 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1289274 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1720. Min Act: -0.0000

Data Index: 414122 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1769. Min Act: -0.0000

Data Index: 219234 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1020396 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1288647 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1320685 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1078247 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1555. Min Act: -0.0000

Data Index: 81592 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1739. Min Act: -0.0000

Data Index: 378329 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1191578 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1572. Min Act: -0.0000

Data Index: 382110 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.2857. Min Range: -0.2857

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1421918 (Python Code)

Max Activating Token Index: 113