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

Dataset: The Pile

Neuron 1130 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.4375. Min Act: -0.0000

Data Index: 50431 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.3158. Min Act: -0.0000

Data Index: 819865 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1170606 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1864443 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2860. Min Act: -0.0000

Data Index: 145758 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.3211. Min Act: -0.0000

Data Index: 570081 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1624. Min Act: -0.0000

Data Index: 409328 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1100082 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2204. Min Act: -0.0000

Data Index: 327618 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1215397 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1164720 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1466408 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1517. Min Act: -0.0000

Data Index: 651353 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1395. Min Act: -0.0000

Data Index: 345552 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2015. Min Act: -0.0000

Data Index: 1192953 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1077. Min Act: -0.0000

Data Index: 19281 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1302850 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1024. Min Act: -0.0000

Data Index: 986456 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2375. Min Act: -0.0000

Data Index: 574605 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2445. Min Act: -0.0000

Data Index: 93982 (The Pile)

Max Activating Token Index: 860