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

Dataset: The Pile

Neuron 1832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1135360 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7653. Min Act: -0.0000

Data Index: 367978 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1777889 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1648634 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7396. Min Act: -0.0000

Data Index: 722506 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6950. Min Act: -0.0000

Data Index: 865167 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1925233 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7363. Min Act: -0.0000

Data Index: 892751 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7376. Min Act: -0.0000

Data Index: 535524 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1116319 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1292964 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7683. Min Act: -0.0000

Data Index: 363436 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7234. Min Act: -0.0000

Data Index: 601936 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1902522 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1810646 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1466229 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7086. Min Act: -0.0000

Data Index: 941985 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1642182 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6858. Min Act: -0.0000

Data Index: 653621 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1174525 (The Pile)

Max Activating Token Index: 613