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

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

Neuron 2890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0821. Min Act: -0.0002

Data Index: 494305 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0713. Min Act: -0.0002

Data Index: 313353 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0002

Data Index: 238327 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1180780 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1227928 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1296385 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0747. Min Act: -0.0002

Data Index: 982378 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1272747 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1015466 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1270542 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0676. Min Act: -0.0002

Data Index: 176722 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0707. Min Act: -0.0002

Data Index: 375368 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0633. Min Act: -0.0002

Data Index: 620298 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0731. Min Act: -0.0002

Data Index: 292828 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0690. Min Act: -0.0002

Data Index: 525266 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1183600 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0767. Min Act: -0.0002

Data Index: 57305 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1308903 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0676. Min Act: -0.0002

Data Index: 917152 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1225366 (C4 (Web Text))

Max Activating Token Index: 689