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

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

Neuron 2681 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: 2.1057. Min Range: -2.1057

Max Act: 2.1057. Min Act: -0.0000

Data Index: 754192 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.6465. Min Act: -0.0000

Data Index: 526880 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1244594 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.4621. Min Act: -0.0000

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1116443 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.3009. Min Act: -0.0000

Data Index: 328673 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.3026. Min Act: -0.0000

Data Index: 845279 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1745. Min Act: -0.0000

Data Index: 811387 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1529. Min Act: -0.0000

Data Index: 994629 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1153349 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1101. Min Act: -0.0000

Data Index: 572437 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1316901 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1292395 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1620173 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.0722. Min Act: -0.0000

Data Index: 97998 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.0633. Min Act: -0.0000

Data Index: 934185 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1071454 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 2.1057. Min Range: -2.1057

Max Act: 0.9667. Min Act: -0.0000

Data Index: 926879 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1056325 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.1057. Min Range: -2.1057

Max Act: 1.0259. Min Act: -0.0000

Data Index: 2137 (C4 (Web Text))

Max Activating Token Index: 307