Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0006

Data Index: 814911 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0005

Data Index: 990935 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0006

Data Index: 403030 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1392431 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0006

Data Index: 643388 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0006

Data Index: 952067 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0006

Data Index: 271979 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0006

Data Index: 539158 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0006

Data Index: 884977 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1095145 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1247850 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1619825 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1429448 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0006

Data Index: 343721 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1566972 (Python Code)

Max Activating Token Index: 777

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0006

Data Index: 117549 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0006

Data Index: 894063 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0006

Data Index: 76288 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1115990 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0050. Min Act: -0.0006

Data Index: 492957 (C4 (Web Text))

Max Activating Token Index: 209