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

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

Neuron 5018 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: 5.5608. Min Range: -5.5608

Max Act: 5.5608. Min Act: -0.0001

Data Index: 1374759 (Python Code)

Max Activating Token Index: 196

Text #1

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.8553. Min Act: -0.0001

Data Index: 1537532 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.5454. Min Act: -0.0001

Data Index: 1413966 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.3409. Min Act: -0.0001

Data Index: 1503909 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.4121. Min Act: -0.0001

Data Index: 1653057 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.5148. Min Act: -0.0001

Data Index: 1583716 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.1647. Min Act: -0.0001

Data Index: 1438221 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.2785. Min Act: -0.0001

Data Index: 1605955 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.3886. Min Act: -0.0001

Data Index: 1425040 (Python Code)

Max Activating Token Index: 327

Text #9

Max Range: 5.5608. Min Range: -5.5608

Max Act: 3.8756. Min Act: -0.0001

Data Index: 1479571 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.1599. Min Act: -0.0001

Data Index: 1601104 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.3100. Min Act: -0.0001

Data Index: 1562101 (Python Code)

Max Activating Token Index: 157

Text #12

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.0860. Min Act: -0.0001

Data Index: 1651703 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.0660. Min Act: -0.0001

Data Index: 1449413 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 5.5608. Min Range: -5.5608

Max Act: 3.7441. Min Act: -0.0001

Data Index: 1578592 (Python Code)

Max Activating Token Index: 727

Text #15

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.3096. Min Act: -0.0001

Data Index: 1361899 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.0830. Min Act: -0.0001

Data Index: 1435569 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 5.5608. Min Range: -5.5608

Max Act: 4.2246. Min Act: -0.0001

Data Index: 1397231 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 5.5608. Min Range: -5.5608

Max Act: 3.8893. Min Act: -0.0001

Data Index: 1467527 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 5.5608. Min Range: -5.5608

Max Act: 3.7004. Min Act: -0.0001

Data Index: 1369270 (Python Code)

Max Activating Token Index: 352