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

Dataset: The Pile

Neuron 1412 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1374133 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1837402 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1595080 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1740952 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1882199 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5215. Min Act: -0.0000

Data Index: 896210 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4944. Min Act: -0.0000

Data Index: 663822 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4785. Min Act: -0.0000

Data Index: 525860 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1688941 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1465442 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1751174 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4304. Min Act: -0.0000

Data Index: 800331 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1441033 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4219. Min Act: -0.0000

Data Index: 343749 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4142. Min Act: -0.0000

Data Index: 725528 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4198. Min Act: -0.0000

Data Index: 879260 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4056. Min Act: -0.0000

Data Index: 440151 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4226. Min Act: -0.0000

Data Index: 627951 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4396. Min Act: -0.0000

Data Index: 810205 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.6827. Min Range: -0.6827

Max Act: 0.4362. Min Act: -0.0000

Data Index: 906570 (The Pile)

Max Activating Token Index: 668