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

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

Neuron 3498 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: 4.4391. Min Range: -4.4391

Max Act: 4.4391. Min Act: -0.0000

Data Index: 1402671 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 4.4391. Min Range: -4.4391

Max Act: 4.1581. Min Act: -0.0000

Data Index: 1602911 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.7474. Min Act: -0.0000

Data Index: 1516646 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1396788 (Python Code)

Max Activating Token Index: 808

Text #4

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.8919. Min Act: -0.0000

Data Index: 1548088 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.3806. Min Act: -0.0000

Data Index: 1361080 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.4217. Min Act: -0.0000

Data Index: 1582314 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1599405 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.4352. Min Act: -0.0000

Data Index: 1530332 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.7576. Min Act: -0.0000

Data Index: 1480998 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.2695. Min Act: -0.0000

Data Index: 1442639 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.3939. Min Act: -0.0000

Data Index: 1532609 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.3682. Min Act: -0.0000

Data Index: 1596786 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1647649 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.1309. Min Act: -0.0000

Data Index: 1533040 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.1400. Min Act: -0.0000

Data Index: 1461698 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.4236. Min Act: -0.0000

Data Index: 1374318 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 4.4391. Min Range: -4.4391

Max Act: 2.9902. Min Act: -0.0000

Data Index: 1413216 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1591771 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 4.4391. Min Range: -4.4391

Max Act: 3.4332. Min Act: -0.0000

Data Index: 1594311 (Python Code)

Max Activating Token Index: 759