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

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

Neuron 1077 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: 0.7514. Min Range: -0.7514

Max Act: 0.6688. Min Act: -0.0000

Data Index: 546212 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7514. Min Act: -0.0000

Data Index: 961980 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6850. Min Act: -0.0000

Data Index: 27253 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1067073 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1046251 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5743. Min Act: -0.0000

Data Index: 194464 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1024488 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6124. Min Act: -0.0000

Data Index: 583990 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1032445 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6017. Min Act: -0.0000

Data Index: 585469 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5816. Min Act: -0.0000

Data Index: 324716 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5517. Min Act: -0.0000

Data Index: 874929 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5693. Min Act: -0.0000

Data Index: 400918 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5469. Min Act: -0.0000

Data Index: 410924 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6072. Min Act: -0.0000

Data Index: 913123 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1165291 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5342. Min Act: -0.0000

Data Index: 504729 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1302010 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5344. Min Act: -0.0000

Data Index: 802642 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5211. Min Act: -0.0000

Data Index: 577492 (C4 (Web Text))

Max Activating Token Index: 89