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

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

Neuron 69 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0006

Data Index: 594173 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0006

Data Index: 207034 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1419070 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1244742 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0004

Data Index: 671779 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0006

Data Index: 324198 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1594197 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0006

Data Index: 865817 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1444511 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1437872 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0006

Data Index: 324950 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0005

Data Index: 980850 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0006

Data Index: 494580 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1577774 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1447105 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1458512 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0006

Data Index: 433626 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1434013 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1435034 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1418907 (Python Code)

Max Activating Token Index: 738