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

Dataset: The Pile

Neuron 2624 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4219. Min Range: -5.4219

Max Act: 5.1387. Min Act: -0.0000

Data Index: 18408 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 5.4219. Min Range: -5.4219

Max Act: 5.4219. Min Act: -0.0001

Data Index: 862782 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.9083. Min Act: -0.0000

Data Index: 1253895 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 5.4219. Min Range: -5.4219

Max Act: 5.2786. Min Act: -0.0000

Data Index: 1739953 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.9088. Min Act: -0.0000

Data Index: 322077 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.3741. Min Act: -0.0000

Data Index: 726795 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.4613. Min Act: -0.0000

Data Index: 1937340 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.5053. Min Act: -0.0000

Data Index: 945719 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.3675. Min Act: -0.0000

Data Index: 611605 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.5408. Min Act: -0.0000

Data Index: 1977586 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.3710. Min Act: -0.0000

Data Index: 265577 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.4014. Min Act: -0.0000

Data Index: 590118 (The Pile)

Max Activating Token Index: 123

Text #12

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.1566. Min Act: -0.0000

Data Index: 893550 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.3480. Min Act: -0.0000

Data Index: 1215086 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.4711. Min Act: -0.0000

Data Index: 25396 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.2129. Min Act: -0.0000

Data Index: 894829 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.3363. Min Act: -0.0000

Data Index: 1491761 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 5.4219. Min Range: -5.4219

Max Act: 3.9598. Min Act: -0.0000

Data Index: 59149 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.2704. Min Act: -0.0000

Data Index: 135803 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 5.4219. Min Range: -5.4219

Max Act: 4.1184. Min Act: -0.0000

Data Index: 1733992 (The Pile)

Max Activating Token Index: 1001