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

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

Neuron 1390 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.9087. Min Act: -0.0000

Data Index: 923463 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.8299. Min Act: -0.0000

Data Index: 623764 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.7300. Min Act: -0.0000

Data Index: 165447 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1095772 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6168. Min Act: -0.0000

Data Index: 965987 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5661. Min Act: -0.0000

Data Index: 850647 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5201. Min Act: -0.0000

Data Index: 583612 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1335653 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4707. Min Act: -0.0000

Data Index: 923246 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4700. Min Act: -0.0000

Data Index: 968595 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4461. Min Act: -0.0000

Data Index: 257417 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4256. Min Act: -0.0000

Data Index: 514890 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.3930. Min Act: 0.0000

Data Index: 612651 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4005. Min Act: -0.0000

Data Index: 489706 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4031. Min Act: -0.0000

Data Index: 924756 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4095. Min Act: -0.0000

Data Index: 522571 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4067. Min Act: -0.0000

Data Index: 766132 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.3922. Min Act: -0.0000

Data Index: 846647 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4050. Min Act: 0.0000

Data Index: 85416 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.3997. Min Act: -0.0000

Data Index: 734135 (C4 (Web Text))

Max Activating Token Index: 726