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

Dataset: The Pile

Neuron 2290 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: 0.5984. Min Range: -0.5984

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1891447 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5683. Min Act: -0.0000

Data Index: 528968 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1963193 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1463195 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1987797 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1842166 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5057. Min Act: -0.0000

Data Index: 829754 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1063595 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1444517 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4684. Min Act: 0.0000

Data Index: 154207 (The Pile)

Max Activating Token Index: 965

Text #10

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5294. Min Act: -0.0000

Data Index: 645193 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1641875 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.5038. Min Act: -0.0000

Data Index: 464810 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4401. Min Act: -0.0000

Data Index: 646417 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4611. Min Act: -0.0000

Data Index: 370781 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4651. Min Act: -0.0000

Data Index: 882499 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1748704 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1068533 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4371. Min Act: -0.0000

Data Index: 100189 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.5984. Min Range: -0.5984

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1480153 (The Pile)

Max Activating Token Index: 285