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

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

Neuron 4248 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0590. Min Act: -0.0001

Data Index: 157208 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1301646 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0664. Min Act: -0.0001

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0705. Min Act: -0.0001

Data Index: 926520 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0785. Min Act: -0.0001

Data Index: 814360 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1174444 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1640988 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0641. Min Act: -0.0001

Data Index: 225045 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0624. Min Act: -0.0001

Data Index: 647445 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0639. Min Act: -0.0001

Data Index: 799593 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1446298 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1557093 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0536. Min Act: -0.0001

Data Index: 266392 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0546. Min Act: -0.0001

Data Index: 58950 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0564. Min Act: -0.0001

Data Index: 80691 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1010619 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0530. Min Act: -0.0001

Data Index: 487213 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0512. Min Act: -0.0001

Data Index: 640894 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0528. Min Act: -0.0001

Data Index: 903214 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0611. Min Act: -0.0001

Data Index: 83569 (C4 (Web Text))

Max Activating Token Index: 833