Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2211 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1079121 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 897084 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1330159 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1097359 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 544136 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0004

Data Index: 960256 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0004

Data Index: 938520 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0003

Data Index: 70415 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0004

Data Index: 623119 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0004

Data Index: 618861 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0003

Data Index: 369970 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0060. Min Act: -0.0004

Data Index: 55073 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0061. Min Act: -0.0004

Data Index: 1261057 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0060. Min Act: -0.0004

Data Index: 271739 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1263996 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0059. Min Act: -0.0004

Data Index: 334900 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0059. Min Act: -0.0003

Data Index: 839472 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0059. Min Act: -0.0003

Data Index: 125750 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0003

Data Index: 194561 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0058. Min Act: -0.0003

Data Index: 986757 (C4 (Web Text))

Max Activating Token Index: 344