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

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

Neuron 2753 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.2122. Min Act: -0.0002

Data Index: 894463 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.2058. Min Act: -0.0002

Data Index: 56203 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1924. Min Act: -0.0002

Data Index: 896375 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.2111. Min Act: -0.0002

Data Index: 440849 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1880. Min Act: -0.0002

Data Index: 831037 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1884. Min Act: -0.0002

Data Index: 705025 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1859. Min Act: -0.0002

Data Index: 932200 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1229650 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1802. Min Act: -0.0002

Data Index: 712737 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1778. Min Act: -0.0002

Data Index: 742239 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1668. Min Act: -0.0002

Data Index: 1339599 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1148404 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1761. Min Act: -0.0002

Data Index: 1038965 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1687. Min Act: -0.0002

Data Index: 281229 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1680. Min Act: -0.0002

Data Index: 295878 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1644. Min Act: -0.0002

Data Index: 128163 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1567. Min Act: -0.0002

Data Index: 343335 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1792. Min Act: -0.0002

Data Index: 898260 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1627. Min Act: -0.0002

Data Index: 768717 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.2122. Min Range: -0.2122

Max Act: 0.1603. Min Act: -0.0002

Data Index: 1151987 (C4 (Web Text))

Max Activating Token Index: 714