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

Dataset: The Pile

Neuron 468 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: 1.8456. Min Range: -1.8456

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1511276 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.8287. Min Act: -0.0000

Data Index: 827880 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1090660 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1586685 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5669. Min Act: -0.0000

Data Index: 288224 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1021032 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6162. Min Act: -0.0000

Data Index: 357403 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5643. Min Act: -0.0000

Data Index: 1529239 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6976. Min Act: -0.0000

Data Index: 1179892 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1102974 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1619868 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4089. Min Act: -0.0000

Data Index: 165514 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3694. Min Act: -0.0000

Data Index: 1840878 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5037. Min Act: -0.0000

Data Index: 455998 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1560079 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4755. Min Act: -0.0000

Data Index: 161125 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1897817 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4722. Min Act: -0.0000

Data Index: 67988 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.5240. Min Act: -0.0000

Data Index: 665860 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3511. Min Act: -0.0000

Data Index: 677279 (The Pile)

Max Activating Token Index: 397