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

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

Neuron 2011 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1536907 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.3908. Min Act: -0.0000

Data Index: 1416521 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.3261. Min Act: -0.0000

Data Index: 1583079 (Python Code)

Max Activating Token Index: 934

Text #3

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0696. Min Act: -0.0000

Data Index: 1497466 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1732. Min Act: -0.0000

Data Index: 1523388 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1397. Min Act: -0.0000

Data Index: 1479290 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 2.3908. Min Range: -2.3908

Max Act: 1.9296. Min Act: -0.0000

Data Index: 1558750 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0025. Min Act: -0.0000

Data Index: 1651603 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1267. Min Act: -0.0000

Data Index: 1380365 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0294. Min Act: -0.0000

Data Index: 1479664 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0121. Min Act: -0.0000

Data Index: 1419167 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1243. Min Act: -0.0000

Data Index: 1596269 (Python Code)

Max Activating Token Index: 829

Text #12

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1290. Min Act: -0.0000

Data Index: 1423398 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1347. Min Act: -0.0000

Data Index: 1532032 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0293. Min Act: -0.0000

Data Index: 1551315 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1478842 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1118. Min Act: -0.0000

Data Index: 1472533 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.1151. Min Act: -0.0000

Data Index: 1428916 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1597807 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 2.3908. Min Range: -2.3908

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1503944 (Python Code)

Max Activating Token Index: 226