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

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

Neuron 1064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3800. Min Act: -0.0000

Data Index: 1263699 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2555. Min Act: -0.0001

Data Index: 329315 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3146. Min Act: -0.0000

Data Index: 347428 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1746. Min Act: -0.0001

Data Index: 1181020 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1396. Min Act: -0.0000

Data Index: 777141 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1260. Min Act: -0.0001

Data Index: 437860 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1159620 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.0354. Min Act: -0.0000

Data Index: 436862 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.9743. Min Act: -0.0000

Data Index: 240174 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1126952 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1326817 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.0084. Min Act: -0.0000

Data Index: 316827 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.9670. Min Act: -0.0000

Data Index: 767280 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.8841. Min Act: -0.0000

Data Index: 3673 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1191060 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1234251 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.8665. Min Act: -0.0000

Data Index: 339231 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.8744. Min Act: -0.0000

Data Index: 557291 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.8962. Min Act: -0.0001

Data Index: 584973 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 1.3800. Min Range: -1.3800

Max Act: 0.9816. Min Act: -0.0000

Data Index: 302345 (C4 (Web Text))

Max Activating Token Index: 574