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

Dataset: The Pile

Neuron 2664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1433374 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1512882 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3989. Min Act: -0.0000

Data Index: 318041 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1018559 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1725881 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1041618 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3803. Min Act: -0.0000

Data Index: 334431 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1913154 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1210022 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1227151 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3507. Min Act: -0.0000

Data Index: 721385 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1892106 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1799322 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1117036 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3905. Min Act: -0.0000

Data Index: 626845 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1710810 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3320. Min Act: -0.0000

Data Index: 257579 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3465. Min Act: -0.0000

Data Index: 743976 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1705435 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.6252. Min Range: -0.6252

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1064440 (The Pile)

Max Activating Token Index: 751