Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6962. Min Act: -0.0000

Data Index: 30667 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1001136 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5853. Min Act: -0.0000

Data Index: 55100 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1006296 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1196525 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1146373 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5389. Min Act: -0.0000

Data Index: 940517 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5097. Min Act: -0.0000

Data Index: 206381 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4763. Min Act: -0.0000

Data Index: 740385 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5069. Min Act: -0.0000

Data Index: 707410 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5082. Min Act: -0.0000

Data Index: 819751 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5185. Min Act: -0.0000

Data Index: 644558 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4965. Min Act: -0.0000

Data Index: 841903 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4764. Min Act: -0.0000

Data Index: 323186 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.5063. Min Act: -0.0000

Data Index: 405574 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4746. Min Act: -0.0000

Data Index: 196258 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1317440 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4756. Min Act: -0.0000

Data Index: 952674 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4619. Min Act: -0.0000

Data Index: 889715 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.6962. Min Range: -0.6962

Max Act: 0.4443. Min Act: -0.0000

Data Index: 161340 (C4 (Web Text))

Max Activating Token Index: 965