Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1020. Min Act: -0.0002

Data Index: 783452 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1073290 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0980. Min Act: -0.0002

Data Index: 424783 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1043. Min Act: -0.0001

Data Index: 322610 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1055. Min Act: -0.0002

Data Index: 61425 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1020. Min Act: -0.0002

Data Index: 540688 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1056. Min Act: -0.0002

Data Index: 276823 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0001

Data Index: 147419 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1317442 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1035. Min Act: -0.0002

Data Index: 109948 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0974. Min Act: -0.0002

Data Index: 39349 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1006. Min Act: -0.0002

Data Index: 123765 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0940. Min Act: -0.0002

Data Index: 575919 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0941. Min Act: -0.0002

Data Index: 942748 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0962. Min Act: -0.0001

Data Index: 650086 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1064117 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0864. Min Act: -0.0002

Data Index: 324871 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0862. Min Act: -0.0002

Data Index: 319270 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0885. Min Act: -0.0002

Data Index: 926707 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0838. Min Act: -0.0002

Data Index: 924578 (C4 (Web Text))

Max Activating Token Index: 549