Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1531081 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1643074 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1489711 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1458816 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1427147 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1594041 (Python Code)

Max Activating Token Index: 878

Text #6

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1596904 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1586702 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1599854 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1537445 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1528783 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1594926 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1637792 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1415517 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1652852 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1597226 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1419707 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4685. Min Act: -0.0001

Data Index: 1519360 (Python Code)

Max Activating Token Index: 762

Text #18

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1594756 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1634415 (Python Code)

Max Activating Token Index: 735