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

Dataset: The Pile

Neuron 3901 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5680. Min Act: -0.0000

Data Index: 921697 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5168. Min Act: -0.0000

Data Index: 592743 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1501992 (The Pile)

Max Activating Token Index: 727

Text #3

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5129. Min Act: -0.0000

Data Index: 494264 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1475930 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1730782 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4465. Min Act: -0.0000

Data Index: 356205 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1551032 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1666181 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4390. Min Act: -0.0000

Data Index: 675898 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4530. Min Act: -0.0000

Data Index: 277183 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4436. Min Act: -0.0000

Data Index: 266812 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4602. Min Act: -0.0000

Data Index: 771975 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4314. Min Act: -0.0000

Data Index: 659474 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1729355 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1243014 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1917774 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4572. Min Act: -0.0000

Data Index: 500906 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1427992 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.5680. Min Range: -0.5680

Max Act: 0.4280. Min Act: -0.0000

Data Index: 782 (The Pile)

Max Activating Token Index: 311