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

Dataset: The Pile

Neuron 2762 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6482. Min Act: -0.0000

Data Index: 417518 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1892509 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1718519 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1891621 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1199123 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1328505 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2984. Min Act: -0.0000

Data Index: 813850 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1348151 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2882. Min Act: -0.0000

Data Index: 670347 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2910. Min Act: -0.0000

Data Index: 587321 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3784. Min Act: -0.0000

Data Index: 106315 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3220. Min Act: -0.0000

Data Index: 436215 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3813. Min Act: -0.0000

Data Index: 1389445 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.3295. Min Act: -0.0000

Data Index: 18847 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2053. Min Act: -0.0000

Data Index: 337770 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2803. Min Act: -0.0000

Data Index: 828013 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1596903 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1655973 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1028503 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.2050. Min Act: -0.0000

Data Index: 14613 (The Pile)

Max Activating Token Index: 700