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

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

Neuron 589 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: 0.7858. Min Range: -0.7858

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1362847 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1466588 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1475632 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1624709 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1500900 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1594665 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1625427 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1551625 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1551418 (Python Code)

Max Activating Token Index: 891

Text #9

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1613878 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1387743 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1426448 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1648500 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1563174 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1364667 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1645482 (Python Code)

Max Activating Token Index: 1001

Text #16

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1510196 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1539639 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1635024 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1518463 (Python Code)

Max Activating Token Index: 583