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

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

Neuron 4092 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: 1.8716. Min Range: -1.8716

Max Act: 1.8553. Min Act: -0.0001

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.8267. Min Act: -0.0001

Data Index: 1130019 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7955. Min Act: -0.0000

Data Index: 119056 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.8716. Min Act: -0.0001

Data Index: 570225 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1084080 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4771. Min Act: -0.0001

Data Index: 643859 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6396. Min Act: -0.0000

Data Index: 313877 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5250. Min Act: -0.0000

Data Index: 898592 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5671. Min Act: -0.0001

Data Index: 24235 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5274. Min Act: -0.0000

Data Index: 621729 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5005. Min Act: -0.0000

Data Index: 111403 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.7766. Min Act: -0.0001

Data Index: 194264 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5862. Min Act: -0.0001

Data Index: 952151 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4839. Min Act: -0.0001

Data Index: 25792 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1113086 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.6668. Min Act: -0.0001

Data Index: 350361 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4668. Min Act: -0.0000

Data Index: 63617 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5296. Min Act: -0.0001

Data Index: 1496167 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.5375. Min Act: -0.0001

Data Index: 1198350 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.8716. Min Range: -1.8716

Max Act: 1.4996. Min Act: -0.0000

Data Index: 691322 (C4 (Web Text))

Max Activating Token Index: 288