Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1669 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1024. Min Act: -0.0002

Data Index: 314741 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0002

Data Index: 435084 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1277124 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0993. Min Act: -0.0002

Data Index: 329241 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0969. Min Act: -0.0002

Data Index: 932539 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1104028 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0948. Min Act: -0.0002

Data Index: 33774 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0940. Min Act: -0.0002

Data Index: 24858 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1095865 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0938. Min Act: -0.0002

Data Index: 42140 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0961. Min Act: -0.0002

Data Index: 952392 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0932. Min Act: -0.0002

Data Index: 325815 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0925. Min Act: -0.0002

Data Index: 739304 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0928. Min Act: -0.0002

Data Index: 583266 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1357411 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1229733 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0929. Min Act: -0.0002

Data Index: 851658 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1166614 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0864. Min Act: -0.0002

Data Index: 674711 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0903. Min Act: -0.0002

Data Index: 104471 (C4 (Web Text))

Max Activating Token Index: 104