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

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

Neuron 1328 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1386008 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7864. Min Act: -0.0000

Data Index: 142962 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.8470. Min Act: -0.0000

Data Index: 913604 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1467650 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7351. Min Act: -0.0000

Data Index: 637592 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1596218 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1539634 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6589. Min Act: -0.0000

Data Index: 337236 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1400485 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1471416 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1538565 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6881. Min Act: -0.0000

Data Index: 45955 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1479019 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1469607 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1647934 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1502210 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.7235. Min Act: -0.0000

Data Index: 923075 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1558547 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1406779 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 0.9385. Min Range: -0.9385

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1374615 (Python Code)

Max Activating Token Index: 354