Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3754. Min Act: -0.0000

Data Index: 93573 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1080698 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3992. Min Act: -0.0001

Data Index: 778757 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1130211 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3520. Min Act: -0.0001

Data Index: 152375 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3314. Min Act: -0.0001

Data Index: 356455 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3417. Min Act: -0.0001

Data Index: 334151 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2935. Min Act: -0.0001

Data Index: 632264 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1322374 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3083. Min Act: -0.0001

Data Index: 559817 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3060. Min Act: -0.0001

Data Index: 825939 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.3041. Min Act: -0.0001

Data Index: 488776 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1185865 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2609. Min Act: -0.0001

Data Index: 880642 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2603. Min Act: -0.0001

Data Index: 965241 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2587. Min Act: -0.0001

Data Index: 679534 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2258. Min Act: -0.0001

Data Index: 688151 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2357. Min Act: -0.0000

Data Index: 362829 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2597. Min Act: -0.0001

Data Index: 2655 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.3992. Min Range: -0.3992

Max Act: 0.2556. Min Act: -0.0001

Data Index: 710947 (C4 (Web Text))

Max Activating Token Index: 54