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

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

Neuron 352 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: 0.1201. Min Range: -0.1201

Max Act: 0.1201. Min Act: -0.0001

Data Index: 718338 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0998. Min Act: -0.0001

Data Index: 169566 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0996. Min Act: -0.0002

Data Index: 197882 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1018. Min Act: -0.0001

Data Index: 110048 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1024. Min Act: -0.0002

Data Index: 506150 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0969. Min Act: -0.0002

Data Index: 483868 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0967. Min Act: -0.0001

Data Index: 491222 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1194508 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1076889 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1140668 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0936. Min Act: -0.0000

Data Index: 537857 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0969. Min Act: -0.0002

Data Index: 31658 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0924. Min Act: -0.0000

Data Index: 724474 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0952. Min Act: -0.0002

Data Index: 713765 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0914. Min Act: -0.0002

Data Index: 895835 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0911. Min Act: -0.0002

Data Index: 754546 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1067072 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1065604 (C4 (Web Text))

Max Activating Token Index: 800