Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 51 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0001

Data Index: 11757 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0976. Min Act: -0.0001

Data Index: 593180 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1241927 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0941. Min Act: -0.0001

Data Index: 967722 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0968. Min Act: -0.0001

Data Index: 903386 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0903. Min Act: -0.0001

Data Index: 99078 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0900. Min Act: -0.0000

Data Index: 713635 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1026302 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1075597 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1314547 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1070069 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0801. Min Act: -0.0001

Data Index: 178172 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0819. Min Act: -0.0001

Data Index: 10628 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0849. Min Act: -0.0000

Data Index: 929225 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0815. Min Act: -0.0001

Data Index: 577814 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0845. Min Act: -0.0000

Data Index: 205375 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1090972 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0718. Min Act: -0.0000

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0777. Min Act: -0.0001

Data Index: 378282 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0776. Min Act: -0.0001

Data Index: 374310 (C4 (Web Text))

Max Activating Token Index: 145