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

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

Neuron 4498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1163. Min Act: -0.0000

Data Index: 759373 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1155. Min Act: -0.0000

Data Index: 392293 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1056. Min Act: -0.0000

Data Index: 439376 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1079. Min Act: -0.0000

Data Index: 395419 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1190753 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1067. Min Act: -0.0000

Data Index: 527643 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1029. Min Act: -0.0000

Data Index: 725065 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1028. Min Act: -0.0000

Data Index: 887861 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1033565 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1254196 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1045. Min Act: -0.0000

Data Index: 740579 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0984. Min Act: -0.0000

Data Index: 681401 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1022. Min Act: -0.0000

Data Index: 404138 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1010. Min Act: -0.0000

Data Index: 131302 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0952. Min Act: -0.0000

Data Index: 281802 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0919. Min Act: -0.0000

Data Index: 601289 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0981. Min Act: -0.0000

Data Index: 705212 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0911. Min Act: -0.0000

Data Index: 817574 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0945. Min Act: -0.0000

Data Index: 111503 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0913. Min Act: -0.0000

Data Index: 744481 (C4 (Web Text))

Max Activating Token Index: 1015