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

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

Neuron 5704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.4734. Min Range: -10.4734

Max Act: 10.4734. Min Act: -0.0001

Data Index: 1413658 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 10.4734. Min Range: -10.4734

Max Act: 9.6364. Min Act: -0.0001

Data Index: 1529239 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 10.4734. Min Range: -10.4734

Max Act: 9.2854. Min Act: -0.0001

Data Index: 1389323 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 10.4734. Min Range: -10.4734

Max Act: 8.0794. Min Act: -0.0001

Data Index: 1401680 (Python Code)

Max Activating Token Index: 360

Text #4

Max Range: 10.4734. Min Range: -10.4734

Max Act: 8.0453. Min Act: -0.0001

Data Index: 1477915 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 10.4734. Min Range: -10.4734

Max Act: 8.0474. Min Act: -0.0001

Data Index: 1570780 (Python Code)

Max Activating Token Index: 889

Text #6

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.5086. Min Act: -0.0001

Data Index: 1616827 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.5233. Min Act: -0.0001

Data Index: 1480497 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.3823. Min Act: -0.0001

Data Index: 1576771 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.4496. Min Act: -0.0001

Data Index: 1367676 (Python Code)

Max Activating Token Index: 579

Text #10

Max Range: 10.4734. Min Range: -10.4734

Max Act: 6.6956. Min Act: -0.0001

Data Index: 1523133 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.5509. Min Act: -0.0001

Data Index: 1408579 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.7304. Min Act: -0.0001

Data Index: 1539626 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.0093. Min Act: -0.0001

Data Index: 1599664 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.1194. Min Act: -0.0001

Data Index: 1378699 (Python Code)

Max Activating Token Index: 722

Text #15

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.4342. Min Act: -0.0001

Data Index: 1430450 (Python Code)

Max Activating Token Index: 282

Text #16

Max Range: 10.4734. Min Range: -10.4734

Max Act: 7.0931. Min Act: -0.0001

Data Index: 1651351 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 10.4734. Min Range: -10.4734

Max Act: 6.8876. Min Act: -0.0001

Data Index: 1506461 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 10.4734. Min Range: -10.4734

Max Act: 6.8821. Min Act: -0.0001

Data Index: 1469513 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 10.4734. Min Range: -10.4734

Max Act: 6.6804. Min Act: -0.0001

Data Index: 1540865 (Python Code)

Max Activating Token Index: 463