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

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

Neuron 3159 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1643961 (Python Code)

Max Activating Token Index: 311

Text #1

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1539923 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1528041 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1409307 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1451812 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1619037 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1472165 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1543381 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1509447 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1464041 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1432691 (Python Code)

Max Activating Token Index: 547

Text #11

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1596754 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1627020 (Python Code)

Max Activating Token Index: 573

Text #13

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1601354 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1458800 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1420558 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1426704 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1371322 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1636996 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.7889. Min Range: -0.7889

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1613963 (Python Code)

Max Activating Token Index: 792