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

Dataset: The Pile

Neuron 1750 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0604. Min Range: -1.0604

Max Act: 1.0604. Min Act: -0.0000

Data Index: 222848 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8489. Min Act: -0.0000

Data Index: 477674 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1194421 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8502. Min Act: -0.0000

Data Index: 316553 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1450817 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1952312 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7637. Min Act: -0.0000

Data Index: 514149 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1477010 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1560283 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1919279 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1468048 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1532467 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7138. Min Act: -0.0000

Data Index: 773640 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6943. Min Act: -0.0000

Data Index: 214516 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1914734 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1503197 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1780882 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1400428 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1550501 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 1.0604. Min Range: -1.0604

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1267923 (The Pile)

Max Activating Token Index: 469