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

Dataset: The Pile

Neuron 4557 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: 1.6325. Min Range: -1.6325

Max Act: 1.6254. Min Act: -0.0000

Data Index: 101890 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1156724 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1436631 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1730755 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4811. Min Act: -0.0000

Data Index: 1341896 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4787. Min Act: -0.0000

Data Index: 384817 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3015. Min Act: -0.0000

Data Index: 197487 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2884. Min Act: -0.0000

Data Index: 778644 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5111. Min Act: -0.0000

Data Index: 1348721 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1911919 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3980. Min Act: -0.0000

Data Index: 324419 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3493. Min Act: -0.0000

Data Index: 412113 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5775. Min Act: -0.0000

Data Index: 560931 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3871. Min Act: -0.0000

Data Index: 471043 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.4118. Min Act: -0.0000

Data Index: 298489 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1617087 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1881921 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2986. Min Act: -0.0000

Data Index: 910436 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1748266 (The Pile)

Max Activating Token Index: 696

Text #19

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.2920. Min Act: -0.0000

Data Index: 417431 (The Pile)

Max Activating Token Index: 463