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

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

Neuron 2296 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: 0.1074. Min Range: -0.1074

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1312264 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0002

Data Index: 10582 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0906. Min Act: -0.0002

Data Index: 731330 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0931. Min Act: -0.0002

Data Index: 307982 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0919. Min Act: -0.0002

Data Index: 865997 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0900. Min Act: -0.0002

Data Index: 772367 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0875. Min Act: -0.0002

Data Index: 941606 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1340182 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0901. Min Act: -0.0002

Data Index: 575627 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0968. Min Act: -0.0002

Data Index: 91180 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1155207 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1075241 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0871. Min Act: -0.0002

Data Index: 70127 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0910. Min Act: -0.0002

Data Index: 560771 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1126699 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0872. Min Act: -0.0002

Data Index: 24312 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0918. Min Act: -0.0002

Data Index: 470589 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1334255 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0882. Min Act: -0.0002

Data Index: 70867 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0808. Min Act: -0.0002

Data Index: 636983 (C4 (Web Text))

Max Activating Token Index: 169