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

Dataset: The Pile

Neuron 1568 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1430. Min Range: -1.1430

Max Act: 1.1430. Min Act: -0.0000

Data Index: 122601 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9471. Min Act: -0.0000

Data Index: 786581 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1609033 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1363385 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1412731 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1764049 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8860. Min Act: -0.0000

Data Index: 687825 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9054. Min Act: -0.0000

Data Index: 483416 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7293. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8360. Min Act: -0.0000

Data Index: 996437 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1794150 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8054. Min Act: -0.0000

Data Index: 209387 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1062618 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1581721 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1297316 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1937633 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 677