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

Dataset: The Pile

Neuron 940 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0160. Min Range: -1.0160

Max Act: 1.0160. Min Act: -0.0000

Data Index: 303564 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1269887 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1084628 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1828877 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1444585 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6032. Min Act: -0.0000

Data Index: 192575 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5891. Min Act: -0.0000

Data Index: 767598 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5477. Min Act: -0.0000

Data Index: 13177 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1530304 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5191. Min Act: -0.0000

Data Index: 793552 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5625. Min Act: -0.0000

Data Index: 514358 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5598. Min Act: -0.0000

Data Index: 632359 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5193. Min Act: -0.0000

Data Index: 83782 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5618. Min Act: -0.0000

Data Index: 396442 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.4797. Min Act: -0.0000

Data Index: 492364 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5264. Min Act: -0.0000

Data Index: 700024 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1515343 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5751. Min Act: -0.0000

Data Index: 207900 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.4918. Min Act: -0.0000

Data Index: 696933 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.4609. Min Act: -0.0000

Data Index: 541646 (The Pile)

Max Activating Token Index: 215