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

Dataset: The Pile

Neuron 3669 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1657996 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8709. Min Act: -0.0000

Data Index: 351914 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1610227 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8136. Min Act: -0.0000

Data Index: 511391 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1605691 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8521. Min Act: -0.0000

Data Index: 828204 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1010114 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1881030 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7546. Min Act: -0.0000

Data Index: 252265 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1049106 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8236. Min Act: -0.0000

Data Index: 841512 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1955607 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1725816 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1954903 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1982555 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.8100. Min Act: -0.0000

Data Index: 884866 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7742. Min Act: -0.0000

Data Index: 169911 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1328955 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1431872 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.8814. Min Range: -0.8814

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1576759 (The Pile)

Max Activating Token Index: 192