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

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

Neuron 5209 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: 0.7196. Min Range: -0.7196

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1615924 (Python Code)

Max Activating Token Index: 896

Text #1

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6873. Min Act: -0.0001

Data Index: 679149 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1178173 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6749. Min Act: -0.0001

Data Index: 1495134 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.7196. Min Act: -0.0001

Data Index: 1248872 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1372901 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6201. Min Act: -0.0001

Data Index: 360550 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6071. Min Act: -0.0000

Data Index: 759548 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1484229 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5896. Min Act: -0.0001

Data Index: 673609 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1542646 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5849. Min Act: -0.0001

Data Index: 33760 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1567998 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5592. Min Act: -0.0001

Data Index: 1512127 (Python Code)

Max Activating Token Index: 199

Text #14

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1625319 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1447491 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5964. Min Act: -0.0001

Data Index: 1643313 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5687. Min Act: -0.0001

Data Index: 1395013 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5264. Min Act: -0.0001

Data Index: 748710 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.7196. Min Range: -0.7196

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1198755 (C4 (Web Text))

Max Activating Token Index: 356