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

Dataset: The Pile

Neuron 1487 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: 3.9479. Min Range: -3.9479

Max Act: 3.9479. Min Act: -0.0000

Data Index: 1673965 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.6989. Min Act: -0.0000

Data Index: 852622 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.5909. Min Act: -0.0000

Data Index: 1964413 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.7413. Min Act: -0.0000

Data Index: 85302 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.5216. Min Act: -0.0000

Data Index: 648809 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.3649. Min Act: -0.0000

Data Index: 1555782 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.1437. Min Act: -0.0000

Data Index: 1647074 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.2705. Min Act: -0.0000

Data Index: 1831597 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.2219. Min Act: -0.0000

Data Index: 610948 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.3406. Min Act: -0.0000

Data Index: 153500 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0123. Min Act: -0.0000

Data Index: 910852 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 3.9479. Min Range: -3.9479

Max Act: 2.9625. Min Act: -0.0000

Data Index: 1057330 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0780. Min Act: -0.0000

Data Index: 1520729 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.2182. Min Act: -0.0000

Data Index: 1790013 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0617. Min Act: -0.0000

Data Index: 650195 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 3.9479. Min Range: -3.9479

Max Act: 2.8976. Min Act: -0.0000

Data Index: 300099 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0265. Min Act: -0.0000

Data Index: 1825324 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0160. Min Act: -0.0000

Data Index: 1830280 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 3.9479. Min Range: -3.9479

Max Act: 2.8795. Min Act: -0.0000

Data Index: 398701 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 3.9479. Min Range: -3.9479

Max Act: 3.0177. Min Act: -0.0000

Data Index: 71635 (The Pile)

Max Activating Token Index: 223