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

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

Neuron 4572 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: 1.2741. Min Range: -1.2741

Max Act: 1.2741. Min Act: -0.0000

Data Index: 710046 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.2741. Min Range: -1.2741

Max Act: 1.1519. Min Act: -0.0000

Data Index: 375209 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.2741. Min Range: -1.2741

Max Act: 1.1214. Min Act: -0.0000

Data Index: 229244 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 1.2741. Min Range: -1.2741

Max Act: 1.1197. Min Act: -0.0000

Data Index: 580200 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9899. Min Act: -0.0000

Data Index: 14860 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9732. Min Act: -0.0000

Data Index: 229775 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9311. Min Act: -0.0000

Data Index: 565239 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9527. Min Act: -0.0000

Data Index: 431172 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1135517 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1009859 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1091787 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1123511 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1157289 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1349398 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.2741. Min Range: -1.2741

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1282899 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8859. Min Act: -0.0000

Data Index: 389533 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1025967 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1185036 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8477. Min Act: -0.0000

Data Index: 627735 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.2741. Min Range: -1.2741

Max Act: 0.8578. Min Act: -0.0000

Data Index: 264224 (C4 (Web Text))

Max Activating Token Index: 571