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

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

Neuron 1641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.6896. Min Act: -0.0001

Data Index: 702196 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4600. Min Act: -0.0001

Data Index: 1318092 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1312563 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1035844 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1235185 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4740. Min Act: -0.0001

Data Index: 287800 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.2501. Min Act: -0.0001

Data Index: 36912 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1944. Min Act: -0.0001

Data Index: 103836 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4492. Min Act: -0.0001

Data Index: 1245981 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1669. Min Act: -0.0001

Data Index: 575344 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1473. Min Act: -0.0001

Data Index: 671931 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.0304. Min Act: -0.0001

Data Index: 259289 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1738. Min Act: -0.0001

Data Index: 1155752 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1467. Min Act: -0.0001

Data Index: 665697 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1579. Min Act: -0.0001

Data Index: 865467 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1813. Min Act: -0.0001

Data Index: 894015 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1730. Min Act: -0.0001

Data Index: 1204331 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1582. Min Act: -0.0001

Data Index: 140817 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.1499. Min Act: -0.0001

Data Index: 760646 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.0754. Min Act: -0.0001

Data Index: 1263128 (C4 (Web Text))

Max Activating Token Index: 565