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

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

Neuron 1396 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.6083. Min Act: -0.0000

Data Index: 1516233 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1398829 (Python Code)

Max Activating Token Index: 560

Text #2

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1555790 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1458691 (Python Code)

Max Activating Token Index: 414

Text #4

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1616218 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1623697 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1590459 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1464107 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3346. Min Act: -0.0000

Data Index: 1579250 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1518403 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1629763 (Python Code)

Max Activating Token Index: 522

Text #11

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1580485 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1434610 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2422. Min Act: -0.0000

Data Index: 1542896 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1422627 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1444700 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1501348 (Python Code)

Max Activating Token Index: 444

Text #17

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1638993 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1431911 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 1.6083. Min Range: -1.6083

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1395844 (Python Code)

Max Activating Token Index: 366