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

Dataset: The Pile

Neuron 1559 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: 3.2744. Min Range: -3.2744

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1783583 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.7715. Min Act: -0.0000

Data Index: 1718523 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.4697. Min Act: -0.0000

Data Index: 1067816 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.4923. Min Act: -0.0000

Data Index: 1926013 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.2936. Min Act: -0.0000

Data Index: 1707236 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.1130. Min Act: -0.0000

Data Index: 1401015 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0937. Min Act: -0.0000

Data Index: 639620 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9886. Min Act: -0.0000

Data Index: 772005 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0893. Min Act: -0.0000

Data Index: 282938 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1108093 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0422. Min Act: -0.0000

Data Index: 84868 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1335370 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1329559 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0206. Min Act: -0.0000

Data Index: 801041 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 3.2744. Min Range: -3.2744

Max Act: 2.0392. Min Act: -0.0000

Data Index: 593429 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8631. Min Act: -0.0000

Data Index: 318432 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9524. Min Act: -0.0000

Data Index: 925935 (The Pile)

Max Activating Token Index: 913

Text #17

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.9370. Min Act: -0.0000

Data Index: 1610339 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1558120 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 3.2744. Min Range: -3.2744

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1887615 (The Pile)

Max Activating Token Index: 273