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

Dataset: The Pile

Neuron 2778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9984. Min Act: -0.0000

Data Index: 188 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.1004. Min Range: -1.1004

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1401336 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 1.1004. Min Range: -1.1004

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1066619 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 1.1004. Min Range: -1.1004

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1279597 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 1.1004. Min Range: -1.1004

Max Act: 1.0192. Min Act: -0.0000

Data Index: 410954 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1231412 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1878364 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9281. Min Act: -0.0000

Data Index: 9200 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8782. Min Act: -0.0000

Data Index: 573763 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1329582 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9092. Min Act: -0.0000

Data Index: 33496 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1400693 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1600130 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8715. Min Act: -0.0000

Data Index: 866809 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9383. Min Act: -0.0000

Data Index: 585105 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8773. Min Act: -0.0000

Data Index: 893467 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1913743 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1859728 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1603416 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.1004. Min Range: -1.1004

Max Act: 0.9243. Min Act: -0.0000

Data Index: 100152 (The Pile)

Max Activating Token Index: 815