Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2417 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.3904. Min Range: -7.3904

Max Act: 7.3904. Min Act: -0.0000

Data Index: 1184341 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.9204. Min Act: -0.0000

Data Index: 764159 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.7850. Min Act: -0.0000

Data Index: 1231606 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.7664. Min Act: -0.0000

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.5136. Min Act: -0.0000

Data Index: 1347018 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.3773. Min Act: -0.0000

Data Index: 90173 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6192. Min Act: -0.0000

Data Index: 1184985 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.7830. Min Act: -0.0000

Data Index: 1268860 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 7.3904. Min Range: -7.3904

Max Act: 5.6298. Min Act: -0.0000

Data Index: 1355342 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6372. Min Act: -0.0000

Data Index: 728769 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 7.3904. Min Range: -7.3904

Max Act: 5.8487. Min Act: -0.0000

Data Index: 1031414 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.0647. Min Act: -0.0000

Data Index: 419386 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.7926. Min Act: -0.0000

Data Index: 422979 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.0579. Min Act: -0.0000

Data Index: 853158 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 7.3904. Min Range: -7.3904

Max Act: 5.8640. Min Act: -0.0000

Data Index: 475723 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.1743. Min Act: -0.0000

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.4908. Min Act: -0.0000

Data Index: 1314977 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6667. Min Act: -0.0000

Data Index: 933017 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.6859. Min Act: -0.0000

Data Index: 896887 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 7.3904. Min Range: -7.3904

Max Act: 6.3170. Min Act: -0.0000

Data Index: 1145352 (C4 (Web Text))

Max Activating Token Index: 725