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

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

Neuron 1141 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: 1.0210. Min Range: -1.0210

Max Act: 0.9867. Min Act: -0.0001

Data Index: 332274 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0017. Min Act: -0.0001

Data Index: 541754 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1005369 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9906. Min Act: -0.0000

Data Index: 55716 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9906. Min Act: -0.0001

Data Index: 641028 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9906. Min Act: -0.0001

Data Index: 789063 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9906. Min Act: -0.0001

Data Index: 964413 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9906. Min Act: -0.0001

Data Index: 901513 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1277356 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0124. Min Act: -0.0001

Data Index: 235095 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0086. Min Act: -0.0001

Data Index: 692300 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0210. Min Act: -0.0001

Data Index: 472078 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9368. Min Act: -0.0001

Data Index: 1017764 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9727. Min Act: -0.0001

Data Index: 169901 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1246509 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9638. Min Act: -0.0001

Data Index: 616690 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8822. Min Act: -0.0001

Data Index: 977664 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9636. Min Act: -0.0001

Data Index: 13994 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.9269. Min Act: -0.0001

Data Index: 672932 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8709. Min Act: -0.0001

Data Index: 402847 (C4 (Web Text))

Max Activating Token Index: 377