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

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

Neuron 3083 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: 3.0420. Min Range: -3.0420

Max Act: 3.0420. Min Act: -0.0000

Data Index: 966245 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.6821. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.6717. Min Act: -0.0000

Data Index: 1601339 (Python Code)

Max Activating Token Index: 442

Text #3

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.7417. Min Act: -0.0000

Data Index: 1621280 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.8697. Min Act: -0.0000

Data Index: 939085 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.7068. Min Act: -0.0000

Data Index: 1598816 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5401. Min Act: -0.0000

Data Index: 1573138 (Python Code)

Max Activating Token Index: 372

Text #7

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5586. Min Act: -0.0000

Data Index: 1438576 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.6088. Min Act: -0.0000

Data Index: 424731 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.4859. Min Act: -0.0000

Data Index: 1423865 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5882. Min Act: -0.0000

Data Index: 1434633 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.4502. Min Act: -0.0000

Data Index: 1326613 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.4429. Min Act: -0.0000

Data Index: 1515114 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5747. Min Act: -0.0000

Data Index: 1562472 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5740. Min Act: -0.0000

Data Index: 1399215 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5318. Min Act: -0.0000

Data Index: 1512234 (Python Code)

Max Activating Token Index: 975

Text #16

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5765. Min Act: -0.0000

Data Index: 1372274 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.5628. Min Act: -0.0000

Data Index: 1412790 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.6765. Min Act: -0.0000

Data Index: 1462590 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 3.0420. Min Range: -3.0420

Max Act: 2.3882. Min Act: -0.0000

Data Index: 1455208 (Python Code)

Max Activating Token Index: 862