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

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

Neuron 4789 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: 0.1880. Min Range: -0.1880

Max Act: 0.1880. Min Act: -0.0001

Data Index: 335897 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1073410 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1713. Min Act: -0.0001

Data Index: 734136 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1764. Min Act: -0.0001

Data Index: 104180 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1647. Min Act: -0.0001

Data Index: 794872 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1014954 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1588. Min Act: -0.0000

Data Index: 596237 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1478. Min Act: -0.0000

Data Index: 565355 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1431. Min Act: -0.0000

Data Index: 441655 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1471. Min Act: -0.0000

Data Index: 928597 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1257578 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1466. Min Act: -0.0000

Data Index: 682858 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1322. Min Act: -0.0001

Data Index: 860492 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1521. Min Act: -0.0000

Data Index: 490476 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1175806 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1459. Min Act: -0.0001

Data Index: 371420 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1348. Min Act: -0.0000

Data Index: 816701 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1439. Min Act: -0.0000

Data Index: 769730 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1393. Min Act: -0.0000

Data Index: 255211 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1251. Min Act: -0.0001

Data Index: 327327 (C4 (Web Text))

Max Activating Token Index: 343