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

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

Neuron 639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.8416. Min Act: -0.0001

Data Index: 1600714 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.4756. Min Act: -0.0001

Data Index: 229808 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3747. Min Act: -0.0001

Data Index: 1275280 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3741. Min Act: -0.0001

Data Index: 1264553 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.2966. Min Act: -0.0001

Data Index: 974537 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3684. Min Act: -0.0001

Data Index: 1513453 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3282. Min Act: -0.0001

Data Index: 991791 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3941. Min Act: -0.0001

Data Index: 266361 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3742. Min Act: -0.0001

Data Index: 188653 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.3427. Min Act: -0.0001

Data Index: 759215 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.2409. Min Act: -0.0001

Data Index: 858183 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.2393. Min Act: -0.0001

Data Index: 1150975 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.1016. Min Act: -0.0001

Data Index: 147378 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.2280. Min Act: -0.0001

Data Index: 1307587 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1576426 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.1675. Min Act: -0.0001

Data Index: 306668 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.1505. Min Act: -0.0001

Data Index: 613719 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.1431. Min Act: -0.0001

Data Index: 523288 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.8416. Min Range: -1.8416

Max Act: 0.9911. Min Act: -0.0001

Data Index: 61645 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.8416. Min Range: -1.8416

Max Act: 1.0521. Min Act: -0.0001

Data Index: 910046 (C4 (Web Text))

Max Activating Token Index: 376