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

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

Neuron 3284 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0608. Min Range: -3.0608

Max Act: 3.0608. Min Act: -0.0000

Data Index: 1287859 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.3845. Min Act: -0.0000

Data Index: 1243113 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.5585. Min Act: -0.0000

Data Index: 972750 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.2704. Min Act: -0.0000

Data Index: 898145 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.2265. Min Act: -0.0000

Data Index: 220041 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.0125. Min Act: -0.0000

Data Index: 250016 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9607. Min Act: -0.0000

Data Index: 105855 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.0285. Min Act: -0.0000

Data Index: 373719 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.0388. Min Act: -0.0000

Data Index: 479063 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9816. Min Act: -0.0000

Data Index: 885939 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1053221 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1342388 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9536. Min Act: -0.0000

Data Index: 309850 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.8572. Min Act: -0.0000

Data Index: 1076133 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.8516. Min Act: -0.0000

Data Index: 654017 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9481. Min Act: -0.0000

Data Index: 380741 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9248. Min Act: -0.0000

Data Index: 662210 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 3.0608. Min Range: -3.0608

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1059311 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9049. Min Act: -0.0000

Data Index: 752079 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.0608. Min Range: -3.0608

Max Act: 1.9106. Min Act: -0.0000

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 1022