Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 745 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1895411 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1290614 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6365. Min Act: -0.0000

Data Index: 655906 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4813. Min Act: 0.0000

Data Index: 1244476 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4954. Min Act: -0.0000

Data Index: 441586 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1527751 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1000863 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1325446 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1600916 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5077. Min Act: 0.0000

Data Index: 1666352 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4734. Min Act: -0.0000

Data Index: 309511 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1222488 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4752. Min Act: -0.0000

Data Index: 351748 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1657060 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1601964 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1464050 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4488. Min Act: 0.0000

Data Index: 150039 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4574. Min Act: -0.0000

Data Index: 995818 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1701025 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.4400. Min Act: 0.0000

Data Index: 389252 (The Pile)

Max Activating Token Index: 519