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

Dataset: The Pile

Neuron 2138 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: 0.9902. Min Range: -0.9902

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1224177 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.7947. Min Act: -0.0000

Data Index: 23724 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.7699. Min Act: -0.0000

Data Index: 41042 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.7656. Min Act: -0.0000

Data Index: 621000 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1488722 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6000. Min Act: -0.0000

Data Index: 638856 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1764741 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6106. Min Act: -0.0000

Data Index: 875965 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5963. Min Act: -0.0000

Data Index: 723484 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6299. Min Act: -0.0000

Data Index: 483161 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1797239 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6196. Min Act: -0.0000

Data Index: 235416 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1899019 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5498. Min Act: -0.0000

Data Index: 48638 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5925. Min Act: -0.0000

Data Index: 106864 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6161. Min Act: -0.0000

Data Index: 617624 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5802. Min Act: -0.0000

Data Index: 421211 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1823534 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1934469 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1197352 (The Pile)

Max Activating Token Index: 528