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

Dataset: The Pile

Neuron 1512 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: 0.8216. Min Range: -0.8216

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1955432 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1694825 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.8192. Min Act: -0.0000

Data Index: 591189 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.8138. Min Act: -0.0000

Data Index: 915576 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1226841 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7642. Min Act: -0.0000

Data Index: 370594 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1336286 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1837737 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1764999 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6966. Min Act: -0.0000

Data Index: 285670 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7442. Min Act: -0.0000

Data Index: 899101 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1881798 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1811530 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1886437 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1030448 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6526. Min Act: -0.0000

Data Index: 343142 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1566546 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1824247 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1382765 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.8216. Min Range: -0.8216

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1943451 (The Pile)

Max Activating Token Index: 909