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

Dataset: The Pile

Neuron 2942 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: 1.3528. Min Range: -1.3528

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1319685 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1977881 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9574. Min Act: -0.0000

Data Index: 916678 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 1.3528. Min Range: -1.3528

Max Act: 1.0781. Min Act: -0.0000

Data Index: 683743 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1715350 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8442. Min Act: -0.0000

Data Index: 653543 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1921618 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8246. Min Act: -0.0000

Data Index: 167885 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1577205 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.8513. Min Act: -0.0000

Data Index: 174712 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1182845 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1713617 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7795. Min Act: -0.0000

Data Index: 163130 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7317. Min Act: -0.0000

Data Index: 849840 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7505. Min Act: -0.0000

Data Index: 804689 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1263364 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7284. Min Act: -0.0000

Data Index: 72315 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1352808 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.6984. Min Act: -0.0000

Data Index: 57311 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 1.3528. Min Range: -1.3528

Max Act: 0.7295. Min Act: -0.0000

Data Index: 788055 (The Pile)

Max Activating Token Index: 245