Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3463 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6613. Min Act: -0.0000

Data Index: 938307 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6407. Min Act: -0.0000

Data Index: 961699 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1190619 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6600. Min Act: -0.0001

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6785. Min Act: -0.0000

Data Index: 59718 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1316702 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1159616 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5309. Min Act: -0.0000

Data Index: 912409 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5487. Min Act: -0.0000

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5286. Min Act: -0.0000

Data Index: 870920 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5343. Min Act: -0.0000

Data Index: 171411 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1009577 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5072. Min Act: 0.0000

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5028. Min Act: -0.0000

Data Index: 769160 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4686. Min Act: -0.0001

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1580728 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4651. Min Act: -0.0000

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1608295 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4365. Min Act: -0.0000

Data Index: 407139 (C4 (Web Text))

Max Activating Token Index: 953