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

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

Neuron 4080 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0840. Min Range: -2.0840

Max Act: 2.0840. Min Act: -0.0000

Data Index: 678236 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.7939. Min Act: -0.0000

Data Index: 789441 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.4828. Min Act: -0.0000

Data Index: 493364 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.5332. Min Act: -0.0000

Data Index: 732930 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.3126. Min Act: -0.0000

Data Index: 27182 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1479793 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.2845. Min Act: -0.0000

Data Index: 662075 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1875. Min Act: -0.0000

Data Index: 827072 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.2300. Min Act: -0.0000

Data Index: 76167 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1470380 (Python Code)

Max Activating Token Index: 804

Text #10

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1552166 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1451573 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1006. Min Act: -0.0000

Data Index: 623935 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1440711 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1438902 (Python Code)

Max Activating Token Index: 535

Text #15

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1399783 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1496682 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1361364 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.0713. Min Act: -0.0000

Data Index: 475741 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.0840. Min Range: -2.0840

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1600732 (Python Code)

Max Activating Token Index: 1009