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

Dataset: The Pile

Neuron 5014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1592413 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1739484 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5936. Min Act: -0.0000

Data Index: 817102 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1691590 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5718. Min Act: -0.0000

Data Index: 521615 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5464. Min Act: -0.0000

Data Index: 398066 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5270. Min Act: -0.0000

Data Index: 775509 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5761. Min Act: -0.0000

Data Index: 175018 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5416. Min Act: -0.0000

Data Index: 882476 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5578. Min Act: -0.0000

Data Index: 917052 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1496533 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1639723 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5200. Min Act: -0.0000

Data Index: 449358 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5340. Min Act: -0.0000

Data Index: 341787 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1701918 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1579822 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1771354 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4876. Min Act: -0.0000

Data Index: 879400 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4845. Min Act: -0.0000

Data Index: 628191 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4968. Min Act: -0.0000

Data Index: 94581 (The Pile)

Max Activating Token Index: 53