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

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

Neuron 2471 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: 4.8314. Min Range: -4.8314

Max Act: 4.8314. Min Act: -0.0000

Data Index: 1478349 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.7655. Min Act: -0.0000

Data Index: 1563347 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.7379. Min Act: -0.0000

Data Index: 1588940 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.5357. Min Act: -0.0000

Data Index: 1515574 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.5377. Min Act: -0.0000

Data Index: 1489563 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.5034. Min Act: -0.0000

Data Index: 1561792 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.6277. Min Act: -0.0000

Data Index: 1485505 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.3864. Min Act: -0.0000

Data Index: 1584801 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.5217. Min Act: -0.0000

Data Index: 1609764 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.3579. Min Act: -0.0000

Data Index: 1625918 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.3055. Min Act: -0.0000

Data Index: 1596170 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.2904. Min Act: -0.0000

Data Index: 1362465 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.0900. Min Act: -0.0000

Data Index: 1453005 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 4.8314. Min Range: -4.8314

Max Act: 3.9092. Min Act: -0.0000

Data Index: 1376005 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.0326. Min Act: -0.0000

Data Index: 1421305 (Python Code)

Max Activating Token Index: 812

Text #15

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.2071. Min Act: -0.0000

Data Index: 1372375 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 4.8314. Min Range: -4.8314

Max Act: 3.9970. Min Act: -0.0000

Data Index: 1645700 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.1392. Min Act: -0.0000

Data Index: 1601103 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.1437. Min Act: -0.0000

Data Index: 1378619 (Python Code)

Max Activating Token Index: 858

Text #19

Max Range: 4.8314. Min Range: -4.8314

Max Act: 4.0919. Min Act: -0.0000

Data Index: 1542482 (Python Code)

Max Activating Token Index: 12