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

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

Neuron 1252 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: 1.4353. Min Range: -1.4353

Max Act: 1.4353. Min Act: -0.0002

Data Index: 1061172 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.4353. Min Range: -1.4353

Max Act: 1.1611. Min Act: -0.0002

Data Index: 302388 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.4353. Min Range: -1.4353

Max Act: 1.1584. Min Act: -0.0002

Data Index: 6701 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.4353. Min Range: -1.4353

Max Act: 1.1232. Min Act: -0.0002

Data Index: 1078647 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.4353. Min Range: -1.4353

Max Act: 1.0508. Min Act: -0.0002

Data Index: 486210 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9641. Min Act: -0.0002

Data Index: 944564 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.4353. Min Range: -1.4353

Max Act: 1.0163. Min Act: -0.0002

Data Index: 1005190 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9048. Min Act: -0.0002

Data Index: 51527 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9262. Min Act: -0.0002

Data Index: 1156234 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9424. Min Act: -0.0002

Data Index: 827511 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9127. Min Act: -0.0002

Data Index: 302796 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9538. Min Act: -0.0002

Data Index: 64926 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9407. Min Act: -0.0002

Data Index: 296040 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9739. Min Act: -0.0002

Data Index: 689034 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9230. Min Act: -0.0002

Data Index: 299291 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.8974. Min Act: -0.0002

Data Index: 1109561 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.8843. Min Act: -0.0002

Data Index: 1138588 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.8721. Min Act: -0.0003

Data Index: 869698 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.8202. Min Act: -0.0002

Data Index: 317887 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.4353. Min Range: -1.4353

Max Act: 0.9039. Min Act: -0.0002

Data Index: 397474 (C4 (Web Text))

Max Activating Token Index: 254