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

Dataset: The Pile

Neuron 2993 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: 0.6793. Min Range: -0.6793

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1042363 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.6293. Min Act: -0.0000

Data Index: 904717 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5452. Min Act: -0.0000

Data Index: 375287 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.5324. Min Act: -0.0000

Data Index: 619577 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4370. Min Act: -0.0000

Data Index: 984397 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1787201 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1094285 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1772356 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4106. Min Act: -0.0000

Data Index: 359178 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3829. Min Act: -0.0000

Data Index: 322686 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.4165. Min Act: -0.0000

Data Index: 615132 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3902. Min Act: -0.0000

Data Index: 879964 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1624323 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1382757 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3858. Min Act: -0.0000

Data Index: 962398 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3776. Min Act: -0.0000

Data Index: 450902 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3987. Min Act: -0.0000

Data Index: 395132 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1699046 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3529. Min Act: -0.0000

Data Index: 235034 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.6793. Min Range: -0.6793

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1415404 (The Pile)

Max Activating Token Index: 684