Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1525065 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1232994 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0593. Min Act: -0.0001

Data Index: 835578 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0605. Min Act: -0.0002

Data Index: 963787 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1378194 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0597. Min Act: -0.0002

Data Index: 847780 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1465349 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0002

Data Index: 536025 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0558. Min Act: -0.0001

Data Index: 755869 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0579. Min Act: -0.0002

Data Index: 862053 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1647968 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0556. Min Act: -0.0001

Data Index: 811260 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1478051 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1641894 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1588292 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1629984 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1534786 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1383389 (Python Code)

Max Activating Token Index: 914

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1513311 (Python Code)

Max Activating Token Index: 1021

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0528. Min Act: -0.0001

Data Index: 172958 (C4 (Web Text))

Max Activating Token Index: 808