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

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

Neuron 2229 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.5902. Min Act: -0.0000

Data Index: 99482 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.5635. Min Act: -0.0000

Data Index: 326353 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.3742. Min Act: -0.0000

Data Index: 1378658 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1375953 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1033446 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1290379 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2217. Min Act: -0.0000

Data Index: 741608 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.1019. Min Act: -0.0000

Data Index: 911581 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2092. Min Act: -0.0000

Data Index: 386704 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0641. Min Act: -0.0000

Data Index: 929223 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1332108 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0887. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1203849 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1265874 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1300614 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1264147 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1418320 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1123101 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 1.5902. Min Range: -1.5902

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1065057 (C4 (Web Text))

Max Activating Token Index: 461