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

Dataset: The Pile

Neuron 548 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: 1.4130. Min Range: -1.4130

Max Act: 1.3992. Min Act: -0.0000

Data Index: 717609 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1993221 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.2332. Min Act: -0.0000

Data Index: 231054 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.1797. Min Act: -0.0000

Data Index: 986700 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.2125. Min Act: -0.0000

Data Index: 586078 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1434264 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1192497 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.1626. Min Act: -0.0000

Data Index: 218009 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1636617 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9771. Min Act: -0.0000

Data Index: 36783 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1353937 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.0203. Min Act: -0.0000

Data Index: 778391 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 1.4130. Min Range: -1.4130

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1125576 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9770. Min Act: -0.0000

Data Index: 430806 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1312994 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9824. Min Act: -0.0001

Data Index: 289031 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9862. Min Act: -0.0000

Data Index: 916548 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9426. Min Act: -0.0000

Data Index: 827738 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9689. Min Act: -0.0000

Data Index: 497464 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.4130. Min Range: -1.4130

Max Act: 0.9689. Min Act: -0.0000

Data Index: 669561 (The Pile)

Max Activating Token Index: 567