Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4306 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0001

Data Index: 1615239 (Python Code)

Max Activating Token Index: 489

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1475160 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1644416 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1479181 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1599047 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1533107 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1627852 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1425713 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1600222 (Python Code)

Max Activating Token Index: 876

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1452001 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1603099 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1619963 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1591559 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1416621 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1655911 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1428604 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1370176 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1652970 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1427097 (Python Code)

Max Activating Token Index: 207

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1363124 (Python Code)

Max Activating Token Index: 249