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

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

Neuron 3055 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0951. Min Act: -0.0000

Data Index: 280309 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0000

Data Index: 784150 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0936. Min Act: -0.0000

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0948. Min Act: -0.0000

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1297394 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0887. Min Act: -0.0000

Data Index: 562849 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1040178 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0816. Min Act: -0.0000

Data Index: 677265 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0890. Min Act: -0.0000

Data Index: 685588 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0869. Min Act: -0.0000

Data Index: 170519 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0928. Min Act: -0.0000

Data Index: 25956 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0959. Min Act: -0.0000

Data Index: 285568 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0911. Min Act: -0.0000

Data Index: 557838 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1527947 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1139638 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0865. Min Act: -0.0000

Data Index: 528641 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0829. Min Act: -0.0000

Data Index: 524741 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1117950 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1475548 (Python Code)

Max Activating Token Index: 804