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

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

Neuron 1804 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: 2.3602. Min Range: -2.3602

Max Act: 2.3602. Min Act: -0.0000

Data Index: 1656671 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 2.3602. Min Range: -2.3602

Max Act: 2.2367. Min Act: -0.0000

Data Index: 1409081 (Python Code)

Max Activating Token Index: 502

Text #2

Max Range: 2.3602. Min Range: -2.3602

Max Act: 2.3220. Min Act: -0.0000

Data Index: 1462326 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 2.3602. Min Range: -2.3602

Max Act: 2.3015. Min Act: -0.0000

Data Index: 638366 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1650910 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 2.3602. Min Range: -2.3602

Max Act: 2.0052. Min Act: -0.0000

Data Index: 1415272 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.9421. Min Act: -0.0000

Data Index: 1412058 (Python Code)

Max Activating Token Index: 864

Text #7

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.9679. Min Act: -0.0000

Data Index: 1630609 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1614670 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1469508 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.8759. Min Act: -0.0000

Data Index: 1431345 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.5776. Min Act: -0.0000

Data Index: 1462222 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1530950 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1630583 (Python Code)

Max Activating Token Index: 468

Text #14

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1561585 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.4914. Min Act: -0.0000

Data Index: 1646214 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1361236 (Python Code)

Max Activating Token Index: 704

Text #17

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.4698. Min Act: -0.0000

Data Index: 1509164 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1465280 (Python Code)

Max Activating Token Index: 507

Text #19

Max Range: 2.3602. Min Range: -2.3602

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1616818 (Python Code)

Max Activating Token Index: 641