Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2089 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.4358. Min Act: -0.0001

Data Index: 487597 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3883. Min Act: -0.0001

Data Index: 400674 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.4239. Min Act: -0.0001

Data Index: 1609376 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3424. Min Act: -0.0001

Data Index: 402184 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1530. Min Act: -0.0001

Data Index: 955690 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2244. Min Act: -0.0001

Data Index: 315100 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2630. Min Act: -0.0001

Data Index: 1287904 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1818. Min Act: -0.0001

Data Index: 1432927 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1814. Min Act: -0.0001

Data Index: 1371826 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1917. Min Act: -0.0001

Data Index: 1188531 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0573. Min Act: -0.0001

Data Index: 1594759 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0766. Min Act: -0.0001

Data Index: 774878 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1461. Min Act: -0.0001

Data Index: 1444181 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0714. Min Act: -0.0001

Data Index: 248482 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1316. Min Act: -0.0001

Data Index: 1634720 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1651435 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0747. Min Act: -0.0001

Data Index: 1533421 (Python Code)

Max Activating Token Index: 757

Text #17

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1055. Min Act: -0.0001

Data Index: 1616919 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1599643 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1056. Min Act: -0.0001

Data Index: 173281 (C4 (Web Text))

Max Activating Token Index: 891