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

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

Neuron 6094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.6676. Min Act: -0.0001

Data Index: 1435632 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.8783. Min Act: -0.0001

Data Index: 1373470 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.3417. Min Act: -0.0001

Data Index: 1402250 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.5036. Min Act: -0.0001

Data Index: 1456242 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.1703. Min Act: -0.0001

Data Index: 1542057 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.2268. Min Act: -0.0001

Data Index: 1516505 (Python Code)

Max Activating Token Index: 870

Text #6

Max Range: 3.8783. Min Range: -3.8783

Max Act: 3.0379. Min Act: -0.0001

Data Index: 1423406 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.9601. Min Act: -0.0001

Data Index: 1527984 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.6946. Min Act: -0.0001

Data Index: 1614876 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.6682. Min Act: -0.0001

Data Index: 1380763 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.5040. Min Act: -0.0001

Data Index: 1645102 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.4488. Min Act: -0.0001

Data Index: 1634046 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.4589. Min Act: -0.0001

Data Index: 1650744 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.5773. Min Act: -0.0001

Data Index: 1399862 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.3999. Min Act: -0.0001

Data Index: 1639366 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.3788. Min Act: -0.0001

Data Index: 1440919 (Python Code)

Max Activating Token Index: 672

Text #16

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.4522. Min Act: -0.0001

Data Index: 1464993 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.2843. Min Act: -0.0001

Data Index: 1455968 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.1656. Min Act: -0.0001

Data Index: 1511839 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 3.8783. Min Range: -3.8783

Max Act: 2.1462. Min Act: -0.0001

Data Index: 1597317 (Python Code)

Max Activating Token Index: 101