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

Dataset: The Pile

Neuron 2756 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: 3.1745. Min Range: -3.1745

Max Act: 3.1745. Min Act: -0.0000

Data Index: 887864 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.8340. Min Act: -0.0000

Data Index: 958372 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.6168. Min Act: -0.0000

Data Index: 109200 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.3610. Min Act: -0.0000

Data Index: 541075 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.4459. Min Act: -0.0000

Data Index: 1401116 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.5578. Min Act: -0.0000

Data Index: 868082 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.4855. Min Act: -0.0000

Data Index: 1254584 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.3263. Min Act: -0.0000

Data Index: 710867 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.3712. Min Act: -0.0000

Data Index: 345557 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.1361. Min Act: -0.0000

Data Index: 613903 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.2892. Min Act: -0.0000

Data Index: 382055 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.1435. Min Act: -0.0000

Data Index: 1839442 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.2430. Min Act: -0.0000

Data Index: 1266383 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.2578. Min Act: -0.0000

Data Index: 889155 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.2322. Min Act: -0.0000

Data Index: 639775 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.1372. Min Act: -0.0000

Data Index: 178938 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.1899. Min Act: -0.0000

Data Index: 1800409 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1895737 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 3.1745. Min Range: -3.1745

Max Act: 2.3018. Min Act: -0.0000

Data Index: 635482 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 3.1745. Min Range: -3.1745

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1849366 (The Pile)

Max Activating Token Index: 686