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

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

Neuron 3893 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.6474. Min Act: -0.0000

Data Index: 910631 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.7445. Min Act: -0.0000

Data Index: 1227918 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.7134. Min Act: -0.0000

Data Index: 1004164 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.6589. Min Act: -0.0000

Data Index: 434096 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.4563. Min Act: -0.0000

Data Index: 595042 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.4412. Min Act: -0.0000

Data Index: 132365 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.5425. Min Act: -0.0000

Data Index: 99192 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.5304. Min Act: -0.0000

Data Index: 25087 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.4824. Min Act: -0.0000

Data Index: 1271441 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.3953. Min Act: -0.0000

Data Index: 273749 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.4590. Min Act: -0.0000

Data Index: 740061 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.3076. Min Act: -0.0000

Data Index: 1297057 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.0427. Min Act: -0.0000

Data Index: 1188464 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.2636. Min Act: -0.0000

Data Index: 411855 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.2513. Min Act: -0.0000

Data Index: 168900 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1284261 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.2376. Min Act: -0.0000

Data Index: 138993 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.3558. Min Act: -0.0000

Data Index: 602747 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.3265. Min Act: -0.0000

Data Index: 730791 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.7445. Min Range: -2.7445

Max Act: 2.0793. Min Act: -0.0000

Data Index: 9510 (C4 (Web Text))

Max Activating Token Index: 112