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

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

Neuron 48 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0870. Min Act: -0.0001

Data Index: 515757 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0849. Min Act: -0.0001

Data Index: 697722 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1326862 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1265995 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0835. Min Act: -0.0002

Data Index: 865985 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0734. Min Act: -0.0002

Data Index: 785120 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0780. Min Act: -0.0001

Data Index: 2647 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0799. Min Act: -0.0002

Data Index: 215586 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0799. Min Act: -0.0002

Data Index: 309597 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1088799 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0823. Min Act: -0.0001

Data Index: 122200 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1291168 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0810. Min Act: -0.0001

Data Index: 841036 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0738. Min Act: -0.0002

Data Index: 348560 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0763. Min Act: -0.0002

Data Index: 907166 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1185933 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0607. Min Act: -0.0002

Data Index: 162380 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1224093 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0720. Min Act: -0.0002

Data Index: 817526 (C4 (Web Text))

Max Activating Token Index: 242