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

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

Neuron 3613 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9410. Min Range: -3.9410

Max Act: 3.9410. Min Act: -0.0000

Data Index: 1656744 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 3.9410. Min Range: -3.9410

Max Act: 3.6745. Min Act: -0.0000

Data Index: 1569791 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 3.9410. Min Range: -3.9410

Max Act: 3.4991. Min Act: -0.0000

Data Index: 1430922 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 3.9410. Min Range: -3.9410

Max Act: 3.0708. Min Act: -0.0000

Data Index: 1486221 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.9663. Min Act: -0.0000

Data Index: 1460120 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 3.9410. Min Range: -3.9410

Max Act: 3.0155. Min Act: -0.0000

Data Index: 1411321 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.8652. Min Act: -0.0000

Data Index: 1603554 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1596352 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.7058. Min Act: -0.0000

Data Index: 1645156 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.6733. Min Act: -0.0000

Data Index: 1570605 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.5310. Min Act: -0.0000

Data Index: 1373654 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.6444. Min Act: -0.0000

Data Index: 1612398 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.5657. Min Act: -0.0000

Data Index: 1421146 (Python Code)

Max Activating Token Index: 239

Text #13

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.5553. Min Act: -0.0000

Data Index: 1384587 (Python Code)

Max Activating Token Index: 707

Text #14

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.5121. Min Act: -0.0000

Data Index: 1442370 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.2724. Min Act: -0.0000

Data Index: 1589499 (Python Code)

Max Activating Token Index: 310

Text #16

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.4503. Min Act: -0.0000

Data Index: 1417838 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1652287 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1570407 (Python Code)

Max Activating Token Index: 690

Text #19

Max Range: 3.9410. Min Range: -3.9410

Max Act: 2.2778. Min Act: -0.0000

Data Index: 1403840 (Python Code)

Max Activating Token Index: 375