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

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

Neuron 2567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1129656 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1014597 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1612. Min Act: -0.0002

Data Index: 7062 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1604. Min Act: -0.0002

Data Index: 158916 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1552. Min Act: -0.0003

Data Index: 720724 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1514. Min Act: -0.0002

Data Index: 1304011 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1539. Min Act: -0.0002

Data Index: 5687 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1524. Min Act: -0.0003

Data Index: 580027 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1527. Min Act: -0.0003

Data Index: 118315 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1518. Min Act: -0.0002

Data Index: 991696 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1503. Min Act: -0.0002

Data Index: 1294055 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1451. Min Act: -0.0002

Data Index: 7290 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1437. Min Act: -0.0002

Data Index: 952189 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1477. Min Act: -0.0003

Data Index: 50 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1462. Min Act: -0.0002

Data Index: 571047 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1445. Min Act: -0.0002

Data Index: 979521 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1469. Min Act: -0.0003

Data Index: 1321011 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1249046 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1438. Min Act: -0.0002

Data Index: 827177 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.1783. Min Range: -0.1783

Max Act: 0.1423. Min Act: -0.0003

Data Index: 447498 (C4 (Web Text))

Max Activating Token Index: 620