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

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

Neuron 5298 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5867. Min Act: -0.0000

Data Index: 8127 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5912. Min Act: -0.0000

Data Index: 714207 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1113716 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1103336 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4678. Min Act: -0.0000

Data Index: 273290 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5494. Min Act: -0.0000

Data Index: 65397 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5627. Min Act: -0.0000

Data Index: 767197 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1051568 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5227. Min Act: -0.0000

Data Index: 957857 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5265. Min Act: -0.0000

Data Index: 760936 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4590. Min Act: -0.0000

Data Index: 976483 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4739. Min Act: -0.0000

Data Index: 686834 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1285966 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4530. Min Act: -0.0000

Data Index: 270408 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1190054 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4551. Min Act: -0.0000

Data Index: 762992 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4536. Min Act: -0.0000

Data Index: 852732 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4452. Min Act: -0.0000

Data Index: 27542 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1100264 (C4 (Web Text))

Max Activating Token Index: 585