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

Dataset: The Pile

Neuron 3840 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1604319 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.8398. Min Act: -0.0000

Data Index: 750479 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6705. Min Act: 0.0000

Data Index: 733993 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6611. Min Act: -0.0000

Data Index: 285648 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6429. Min Act: -0.0000

Data Index: 639307 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.6007. Min Act: -0.0000

Data Index: 517788 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5898. Min Act: -0.0000

Data Index: 970054 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5663. Min Act: -0.0000

Data Index: 57006 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1476295 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3986. Min Act: 0.0000

Data Index: 1529913 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4623. Min Act: -0.0000

Data Index: 865099 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4495. Min Act: 0.0000

Data Index: 1381641 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4654. Min Act: -0.0000

Data Index: 436411 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2840. Min Act: -0.0000

Data Index: 819863 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1071708 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3105. Min Act: -0.0000

Data Index: 192560 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3145. Min Act: -0.0000

Data Index: 941707 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3754. Min Act: 0.0000

Data Index: 568270 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1382553 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1792392 (The Pile)

Max Activating Token Index: 48