Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.8631. Min Act: -0.0000

Data Index: 403454 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1869681 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1748186 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1655072 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1846397 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1624521 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1349085 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6624. Min Act: 0.0000

Data Index: 1289360 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6514. Min Act: -0.0000

Data Index: 436655 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1603454 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6101. Min Act: -0.0000

Data Index: 784694 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6321. Min Act: -0.0000

Data Index: 103929 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1907652 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.5917. Min Act: -0.0000

Data Index: 610677 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1852787 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6113. Min Act: -0.0000

Data Index: 107789 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6107. Min Act: 0.0000

Data Index: 1882246 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.5858. Min Act: -0.0000

Data Index: 746748 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.5527. Min Act: -0.0000

Data Index: 17263 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.5446. Min Act: -0.0000

Data Index: 279211 (The Pile)

Max Activating Token Index: 589