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

Dataset: The Pile

Neuron 2121 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: 3.6881. Min Range: -3.6881

Max Act: 3.6881. Min Act: -0.0000

Data Index: 323133 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.3130. Min Act: -0.0000

Data Index: 783739 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6826. Min Act: -0.0000

Data Index: 1495631 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.3299. Min Act: -0.0000

Data Index: 1296742 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1153. Min Act: -0.0000

Data Index: 1722826 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.3903. Min Act: -0.0000

Data Index: 1613235 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1042. Min Act: -0.0000

Data Index: 1361303 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.6310. Min Act: -0.0000

Data Index: 1591390 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.3456. Min Act: -0.0000

Data Index: 1762017 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.3113. Min Act: -0.0000

Data Index: 474382 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.2700. Min Act: -0.0000

Data Index: 1188238 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1058470 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1894. Min Act: -0.0000

Data Index: 1813785 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1588. Min Act: -0.0000

Data Index: 948275 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.2911. Min Act: -0.0000

Data Index: 1272542 (The Pile)

Max Activating Token Index: 4

Text #15

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1481. Min Act: -0.0000

Data Index: 1545282 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.2568. Min Act: -0.0000

Data Index: 11732 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.1643. Min Act: -0.0000

Data Index: 615955 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.2469. Min Act: -0.0000

Data Index: 1578380 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 3.6881. Min Range: -3.6881

Max Act: 3.0645. Min Act: -0.0000

Data Index: 1675418 (The Pile)

Max Activating Token Index: 86