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

Dataset: The Pile

Neuron 708 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: 1.3609. Min Range: -1.3609

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1835844 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1526190 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1145468 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1488646 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1481607 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0857. Min Act: -0.0000

Data Index: 455482 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0946. Min Act: -0.0000

Data Index: 564642 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1574919 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9763. Min Act: -0.0000

Data Index: 495007 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9966. Min Act: -0.0000

Data Index: 845813 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0574. Min Act: -0.0000

Data Index: 253420 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1798563 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0274. Min Act: -0.0000

Data Index: 332301 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1671579 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1447360 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1873524 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.3609. Min Range: -1.3609

Max Act: 1.0488. Min Act: -0.0000

Data Index: 536679 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1849369 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1484249 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.3609. Min Range: -1.3609

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1798785 (The Pile)

Max Activating Token Index: 275