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

Dataset: The Pile

Neuron 1277 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9799. Min Act: -0.0000

Data Index: 699057 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1971008 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1591794 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1339426 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1083071 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1561405 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1553099 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1077004 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1406325 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1799529 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7374. Min Act: -0.0000

Data Index: 465261 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7122. Min Act: -0.0000

Data Index: 342479 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.5888. Min Act: -0.0000

Data Index: 245333 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6871. Min Act: -0.0000

Data Index: 227050 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1737186 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.7014. Min Act: -0.0000

Data Index: 491451 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1167761 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6548. Min Act: -0.0000

Data Index: 956815 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1834981 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1534156 (The Pile)

Max Activating Token Index: 958