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

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

Neuron 4250 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1313. Min Range: -2.1313

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1482141 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1523334 (Python Code)

Max Activating Token Index: 673

Text #2

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.8847. Min Act: -0.0000

Data Index: 1534225 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1647868 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.7023. Min Act: -0.0000

Data Index: 1417600 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1579023 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1401997 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.6793. Min Act: -0.0000

Data Index: 1535902 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1624847 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1652457 (Python Code)

Max Activating Token Index: 975

Text #10

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1511544 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1574459 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1416654 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1545017 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1367420 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1486744 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1625519 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.4064. Min Act: -0.0000

Data Index: 921769 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1374822 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 2.1313. Min Range: -2.1313

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1615382 (Python Code)

Max Activating Token Index: 133