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

Dataset: The Pile

Neuron 3879 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.1436. Min Act: -0.0000

Data Index: 582029 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1674333 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1256896 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8309. Min Act: -0.0000

Data Index: 693032 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1666417 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7680. Min Act: -0.0000

Data Index: 640407 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1941108 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7229. Min Act: -0.0000

Data Index: 1993607 (The Pile)

Max Activating Token Index: 73

Text #8

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6943. Min Act: -0.0000

Data Index: 542749 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1035318 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6821. Min Act: -0.0000

Data Index: 797435 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7457. Min Act: -0.0000

Data Index: 924581 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1825309 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6802. Min Act: -0.0000

Data Index: 188981 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6749. Min Act: -0.0000

Data Index: 246976 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7105. Min Act: -0.0000

Data Index: 734689 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.7301. Min Act: -0.0000

Data Index: 407396 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1723721 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1485063 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1695965 (The Pile)

Max Activating Token Index: 787