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

Dataset: The Pile

Neuron 4996 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: 1.0613. Min Range: -1.0613

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1477398 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1028125 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7926. Min Act: -0.0000

Data Index: 105130 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.5827. Min Act: -0.0000

Data Index: 897447 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1677990 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1659181 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6234. Min Act: -0.0000

Data Index: 568590 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7414. Min Act: -0.0000

Data Index: 99202 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1462197 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1458264 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1908762 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1925443 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6186. Min Act: -0.0000

Data Index: 524911 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1313196 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1330602 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1309876 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.5766. Min Act: -0.0000

Data Index: 513521 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1184614 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.4798. Min Act: -0.0000

Data Index: 755940 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1730001 (The Pile)

Max Activating Token Index: 1015