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

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

Neuron 1459 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: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1094788 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0986. Min Act: -0.0002

Data Index: 926325 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1005. Min Act: -0.0002

Data Index: 253473 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0974. Min Act: -0.0002

Data Index: 293534 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0897. Min Act: -0.0002

Data Index: 820033 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0906. Min Act: -0.0002

Data Index: 543963 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1013369 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1130687 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1264793 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0850. Min Act: -0.0002

Data Index: 270444 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0850. Min Act: -0.0002

Data Index: 149382 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1348212 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0820. Min Act: -0.0002

Data Index: 740474 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0795. Min Act: -0.0002

Data Index: 888532 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0801. Min Act: -0.0002

Data Index: 849889 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0799. Min Act: -0.0002

Data Index: 873561 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0784. Min Act: -0.0001

Data Index: 370899 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0783. Min Act: -0.0002

Data Index: 969526 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1344596 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0795. Min Act: -0.0002

Data Index: 145666 (C4 (Web Text))

Max Activating Token Index: 255